fix: pass _cancel_sender in RunnerSupervisor test helper

After merging main (api cancellation #1276), the RunnerSupervisor
dataclass requires a _cancel_sender field. Update the test helper
to create and pass this channel.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

.dockerignore

@@ -0,0 +1,15 @@
+.venv/
+.direnv/
+target/
+.git/
+.idea/
+.pytest_cache/
+.ruff_cache/
+dashboard/node_modules/
+dashboard/.svelte-kit/
+dashboard/build/
+dist/
+*.pdb
+**/__pycache__
+**/.DS_Store
+.mlx_typings/

.github/workflows/build-app.yml

@@ -396,7 +396,7 @@ jobs:
           path: output/EXO-${{ env.RELEASE_VERSION }}.dmg
 
       - name: Upload to S3
-        if: env.SPARKLE_S3_BUCKET != '' && github.ref_type == 'tag'
+        if: env.SPARKLE_S3_BUCKET != ''
         env:
           AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_ID }}
           AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
@@ -412,6 +412,12 @@ jobs:
             PREFIX="${PREFIX}/"
           fi
           DMG_NAME="EXO-${RELEASE_VERSION}.dmg"
+
+          if [[ "${{ github.ref_type }}" != "tag" ]]; then
+            aws s3 cp "$DMG_NAME" "s3://${SPARKLE_S3_BUCKET}/${PREFIX}EXO-${GITHUB_SHA}.dmg"
+            exit 0
+          fi
+
           aws s3 cp "$DMG_NAME" "s3://${SPARKLE_S3_BUCKET}/${PREFIX}${DMG_NAME}"
           if [[ "$IS_ALPHA" != "true" ]]; then
             aws s3 cp "$DMG_NAME" "s3://${SPARKLE_S3_BUCKET}/${PREFIX}EXO-latest.dmg"

.github/workflows/e2e.yml

@@ -0,0 +1,44 @@
+name: e2e-tests
+
+on:
+  push:
+    branches:
+      - e2e-tests
+  pull_request:
+    branches:
+      - staging
+      - main
+
+jobs:
+  e2e:
+    runs-on: ubuntu-latest
+    timeout-minutes: 45
+    steps:
+      - name: Free up disk space
+        run: |
+          sudo rm -rf /usr/share/dotnet /usr/local/lib/android /opt/ghc \
+            /opt/hostedtoolcache /usr/local/share/boost /usr/share/swift \
+            /opt/microsoft /opt/az
+          docker system prune -af
+          df -h /
+
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          lfs: false
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Build E2E image with cache
+        uses: docker/build-push-action@v6
+        with:
+          context: .
+          file: e2e/Dockerfile
+          tags: exo-e2e:latest
+          load: true
+          cache-from: type=gha
+          cache-to: type=gha,mode=max
+
+      - name: Run E2E tests
+        run: python3 e2e/run_all.py

.github/workflows/pipeline.yml

@@ -8,33 +8,6 @@ on:
       - main
 
 jobs:
-  typecheck:
-    runs-on: ubuntu-latest
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v4
-        with:
-          lfs: false
-
-      - uses: cachix/install-nix-action@v31
-        with:
-          nix_path: nixpkgs=channel:nixos-unstable
-
-      - uses: cachix/cachix-action@v14
-        name: Configure Cachix
-        with:
-          name: exo
-          authToken: "${{ secrets.CACHIX_AUTH_TOKEN }}"
-
-      - name: Load nix develop environment
-        run: nix run github:nicknovitski/nix-develop/v1
-
-      - name: Sync dependencies
-        run: uv sync --all-packages
-
-      - name: Run type checker
-        run: uv run basedpyright --project pyproject.toml
-
   nix:
     name: Build and check (${{ matrix.system }})
     runs-on: ${{ matrix.runner }}
@@ -142,4 +115,6 @@ jobs:
           # Run pytest outside sandbox (needs GPU access for MLX)
           export HOME="$RUNNER_TEMP"
           export EXO_TESTS=1
+          export EXO_DASHBOARD_DIR="$PWD/dashboard/" 
+          export EXO_RESOURCES_DIR="$PWD/resources" 
           $TEST_ENV/bin/python -m pytest src -m "not slow" --import-mode=importlib

.gitignore

@@ -31,3 +31,10 @@ dashboard/.svelte-kit/
 
 # host config snapshots
 hosts_*.json
+.swp
+
+# bench files
+bench/**/*.json
+
+# tmp
+tmp/models

.mlx_typings/mflux/models/flux/variants/kontext/__init__.pyi

@@ -0,0 +1,7 @@
+"""
+This type stub file was generated by pyright.
+"""
+
+from mflux.models.flux.variants.kontext.flux_kontext import Flux1Kontext
+
+__all__ = ["Flux1Kontext"]

.mlx_typings/mflux/models/flux/variants/kontext/flux_kontext.pyi

@@ -0,0 +1,49 @@
+"""
+This type stub file was generated by pyright.
+"""
+
+from pathlib import Path
+from typing import Any
+
+from mlx import nn
+
+from mflux.models.common.config.model_config import ModelConfig
+from mflux.models.flux.model.flux_text_encoder.clip_encoder.clip_encoder import (
+    CLIPEncoder,
+)
+from mflux.models.flux.model.flux_text_encoder.t5_encoder.t5_encoder import T5Encoder
+from mflux.models.flux.model.flux_transformer.transformer import Transformer
+from mflux.models.flux.model.flux_vae.vae import VAE
+from mflux.utils.generated_image import GeneratedImage
+
+class Flux1Kontext(nn.Module):
+    vae: VAE
+    transformer: Transformer
+    t5_text_encoder: T5Encoder
+    clip_text_encoder: CLIPEncoder
+    bits: int | None
+    lora_paths: list[str] | None
+    lora_scales: list[float] | None
+    prompt_cache: dict[str, Any]
+    tokenizers: dict[str, Any]
+
+    def __init__(
+        self,
+        quantize: int | None = ...,
+        model_path: str | None = ...,
+        lora_paths: list[str] | None = ...,
+        lora_scales: list[float] | None = ...,
+        model_config: ModelConfig = ...,
+    ) -> None: ...
+    def generate_image(
+        self,
+        seed: int,
+        prompt: str,
+        num_inference_steps: int = ...,
+        height: int = ...,
+        width: int = ...,
+        guidance: float = ...,
+        image_path: Path | str | None = ...,
+        image_strength: float | None = ...,
+        scheduler: str = ...,
+    ) -> GeneratedImage: ...

.mlx_typings/mflux/models/flux/variants/kontext/kontext_util.pyi

@@ -0,0 +1,16 @@
+"""
+This type stub file was generated by pyright.
+"""
+
+import mlx.core as mx
+
+from mflux.models.flux.model.flux_vae.vae import VAE
+
+class KontextUtil:
+    @staticmethod
+    def create_image_conditioning_latents(
+        vae: VAE,
+        height: int,
+        width: int,
+        image_path: str,
+    ) -> tuple[mx.array, mx.array]: ...

.mlx_typings/mlx/core/__init__.pyi

@@ -1139,7 +1139,7 @@ class array:
     ) -> array:
         """See :func:`flatten`."""
 
-    def reshape(self, *shape, stream: Stream | Device | None = ...) -> array:
+    def reshape(self, *shape: int, stream: Stream | Device | None = ...) -> array:
         """
         Equivalent to :func:`reshape` but the shape can be passed either as a
         :obj:`tuple` or as separate arguments.
@@ -1222,7 +1222,7 @@ class array:
     ) -> array:
         """See :func:`swapaxes`."""
 
-    def transpose(self, *axes, stream: Stream | Device | None = ...) -> array:
+    def transpose(self, *axes: int, stream: Stream | Device | None = ...) -> array:
         """
         Equivalent to :func:`transpose` but the axes can be passed either as
         a tuple or as separate arguments.
@@ -2366,7 +2366,7 @@ class custom_function:
 def default_device() -> Device:
     """Get the default device."""
 
-def default_stream(device: Device) -> Stream:
+def default_stream(device: Device | DeviceType) -> Stream:
     """Get the device's default stream."""
 
 def degrees(a: array, /, *, stream: Stream | Device | None = ...) -> array:

.mlx_typings/mlx/nn/layers/convolution.pyi

@@ -30,6 +30,9 @@ class Conv1d(Module):
         bias (bool, optional): If ``True`` add a learnable bias to the output.
             Default: ``True``
     """
+
+    weight: mx.array
+    groups: int
     def __init__(
         self,
         in_channels: int,

.mlx_typings/mlx_lm/models/cache.pyi

@@ -11,7 +11,10 @@ import mlx.core as mx
 class Cache(Protocol):
     keys: mx.array
     values: mx.array
-    def update_and_fetch(self, keys: mx.array, values: mx.array) -> None: ...
+    offset: int
+    def update_and_fetch(
+        self, keys: mx.array, values: mx.array
+    ) -> tuple[mx.array, mx.array]: ...
     @property
     def state(self) -> tuple[mx.array, mx.array]: ...
     @state.setter
@@ -87,6 +90,7 @@ def create_attention_mask(
 class _BaseCache(Cache):
     keys: mx.array
     values: mx.array
+    offset: int
     @property
     def state(self) -> tuple[mx.array, mx.array]: ...
     @state.setter

.mlx_typings/mlx_lm/models/deepseek_v3.pyi

@@ -5,6 +5,7 @@ from typing import Any, Dict, Optional
 
 import mlx.core as mx
 import mlx.nn as nn
+from mlx_lm.models.mla import MultiLinear
 
 from .base import BaseModelArgs
 from .switch_layers import SwitchGLU
@@ -60,7 +61,10 @@ class DeepseekV3Attention(nn.Module):
     q_b_proj: nn.Linear
     kv_a_proj_with_mqa: nn.Linear
     kv_a_layernorm: nn.RMSNorm
-    kv_b_proj: nn.Linear
+    # kv_b_proj: nn.Linear
+    embed_q: MultiLinear
+    unembed_out: MultiLinear
+
     o_proj: nn.Linear
     rope: Any
 

.mlx_typings/mlx_lm/models/glm4_moe.pyi

@@ -0,0 +1,153 @@
+from dataclasses import dataclass
+from typing import Any, Dict, Optional
+
+import mlx.core as mx
+import mlx.nn as nn
+
+from .base import BaseModelArgs
+from .switch_layers import SwitchGLU
+
+@dataclass
+class ModelArgs(BaseModelArgs):
+    model_type: str
+    vocab_size: int
+    hidden_size: int
+    intermediate_size: int
+    max_position_embeddings: int
+    moe_intermediate_size: int
+    norm_topk_prob: bool
+    num_attention_heads: int
+    n_group: int
+    head_dim: int
+    topk_group: int
+    n_shared_experts: int
+    n_routed_experts: int
+    routed_scaling_factor: float
+    num_experts_per_tok: int
+    first_k_dense_replace: int
+    num_hidden_layers: int
+    num_key_value_heads: int
+    rms_norm_eps: float
+    rope_theta: float
+    rope_scaling: Optional[Dict[str, Any]]
+    use_qk_norm: bool
+    tie_word_embeddings: bool
+    attention_bias: bool
+    partial_rotary_factor: float
+    scoring_func: str
+    topk_method: str
+
+class Attention(nn.Module):
+    n_heads: int
+    n_kv_heads: int
+    scale: float
+    q_proj: nn.Linear
+    k_proj: nn.Linear
+    v_proj: nn.Linear
+    o_proj: nn.Linear
+    use_qk_norm: bool
+    q_norm: nn.RMSNorm
+    k_norm: nn.RMSNorm
+    rope: nn.RoPE
+
+    def __init__(self, args: ModelArgs) -> None: ...
+    def __call__(
+        self,
+        x: mx.array,
+        mask: Optional[mx.array] = None,
+        cache: Optional[Any] = None,
+    ) -> mx.array: ...
+
+class MLP(nn.Module):
+    config: ModelArgs
+    hidden_size: int
+    intermediate_size: int
+    gate_proj: nn.Linear
+    up_proj: nn.Linear
+    down_proj: nn.Linear
+
+    def __init__(
+        self,
+        config: ModelArgs,
+        hidden_size: Optional[int] = None,
+        intermediate_size: Optional[int] = None,
+    ) -> None: ...
+    def __call__(self, x: mx.array) -> mx.array: ...
+
+class MoEGate(nn.Module):
+    config: ModelArgs
+    top_k: int
+    norm_topk_prob: bool
+    n_routed_experts: int
+    routed_scaling_factor: float
+    n_group: int
+    topk_group: int
+    weight: mx.array
+    e_score_correction_bias: mx.array
+
+    def __init__(self, config: ModelArgs) -> None: ...
+    def __call__(self, x: mx.array) -> tuple[mx.array, mx.array]: ...
+
+class MoE(nn.Module):
+    config: ModelArgs
+    num_experts_per_tok: int
+    switch_mlp: SwitchGLU
+    gate: MoEGate
+    shared_experts: MLP
+    sharding_group: Optional[mx.distributed.Group]
+
+    def __init__(self, config: ModelArgs) -> None: ...
+    def __call__(self, x: mx.array) -> mx.array: ...
+
+class DecoderLayer(nn.Module):
+    self_attn: Attention
+    mlp: MLP | MoE
+    input_layernorm: nn.RMSNorm
+    post_attention_layernorm: nn.RMSNorm
+
+    def __init__(self, config: ModelArgs, layer_idx: int) -> None: ...
+    def __call__(
+        self,
+        x: mx.array,
+        mask: Optional[mx.array] = None,
+        cache: Optional[Any] = None,
+    ) -> mx.array: ...
+
+class LanguageModel(nn.Module):
+    vocab_size: int
+    embed_tokens: nn.Embedding
+    layers: list[DecoderLayer]
+    norm: nn.RMSNorm
+    pipeline_rank: int
+    pipeline_size: int
+    start_idx: int
+    end_idx: Optional[int]
+    num_layers: int
+
+    def __init__(self, config: ModelArgs) -> None: ...
+    def __call__(
+        self,
+        x: mx.array,
+        cache: Optional[Any] = None,
+    ) -> mx.array: ...
+    @property
+    def pipeline_layers(self) -> list[DecoderLayer]: ...
+
+class Model(nn.Module):
+    args: ModelArgs
+    model_type: str
+    model: LanguageModel
+    lm_head: nn.Linear
+
+    def __init__(self, config: ModelArgs) -> None: ...
+    def __call__(
+        self,
+        inputs: mx.array,
+        cache: Optional[Any] = None,
+    ) -> mx.array: ...
+    def sanitize(self, weights: dict[str, Any]) -> dict[str, Any]: ...
+    def shard(self, group: Optional[mx.distributed.Group] = None) -> None: ...
+    @property
+    def layers(self) -> list[DecoderLayer]: ...
+    @property
+    def cast_predicate(self) -> Any: ...

.mlx_typings/mlx_lm/models/qwen3_next.pyi

@@ -0,0 +1,114 @@
+"""Type stubs for mlx_lm.models.qwen3_next"""
+
+from typing import Any, Optional
+
+import mlx.core as mx
+import mlx.nn as nn
+
+from .switch_layers import SwitchGLU
+
+class Qwen3NextMLP(nn.Module):
+    gate_proj: nn.Linear
+    down_proj: nn.Linear
+    up_proj: nn.Linear
+
+    def __init__(self, dim: int, hidden_dim: int) -> None: ...
+    def __call__(self, x: mx.array) -> mx.array: ...
+
+class Qwen3NextGatedDeltaNet(nn.Module):
+    hidden_size: int
+    num_v_heads: int
+    num_k_heads: int
+    head_k_dim: int
+    head_v_dim: int
+    key_dim: int
+    value_dim: int
+    conv_kernel_size: int
+    conv_dim: int
+    conv1d: nn.Conv1d
+    in_proj_qkvz: nn.Linear
+    in_proj_ba: nn.Linear
+    dt_bias: mx.array
+    A_log: mx.array
+    out_proj: nn.Linear
+
+    def __init__(self, config: Any) -> None: ...
+    def __call__(
+        self,
+        inputs: mx.array,
+        mask: Optional[mx.array] = None,
+        cache: Optional[Any] = None,
+    ) -> mx.array: ...
+
+class Qwen3NextAttention(nn.Module):
+    num_attention_heads: int
+    num_key_value_heads: int
+    head_dim: int
+    scale: float
+    q_proj: nn.Linear
+    k_proj: nn.Linear
+    v_proj: nn.Linear
+    o_proj: nn.Linear
+
+    def __init__(self, args: Any) -> None: ...
+    def __call__(
+        self,
+        x: mx.array,
+        mask: Optional[mx.array] = None,
+        cache: Optional[Any] = None,
+    ) -> mx.array: ...
+
+class Qwen3NextSparseMoeBlock(nn.Module):
+    norm_topk_prob: bool
+    num_experts: int
+    top_k: int
+    gate: nn.Linear
+    switch_mlp: SwitchGLU
+    shared_expert: Qwen3NextMLP
+    shared_expert_gate: nn.Linear
+
+    def __init__(self, args: Any) -> None: ...
+    def __call__(self, x: mx.array) -> mx.array: ...
+
+class Qwen3NextDecoderLayer(nn.Module):
+    is_linear: bool
+    linear_attn: Qwen3NextGatedDeltaNet
+    self_attn: Qwen3NextAttention
+    input_layernorm: nn.RMSNorm
+    post_attention_layernorm: nn.RMSNorm
+    mlp: Qwen3NextMLP | Qwen3NextSparseMoeBlock
+
+    def __init__(self, args: Any, layer_idx: int) -> None: ...
+    def __call__(
+        self,
+        x: mx.array,
+        mask: Optional[mx.array] = None,
+        cache: Optional[Any] = None,
+    ) -> mx.array: ...
+
+class Qwen3NextModel(nn.Module):
+    embed_tokens: nn.Embedding
+    layers: list[Qwen3NextDecoderLayer]
+    norm: nn.RMSNorm
+
+    def __init__(self, args: Any) -> None: ...
+    def __call__(
+        self,
+        inputs: mx.array,
+        cache: Optional[Any] = None,
+    ) -> mx.array: ...
+
+class Model(nn.Module):
+    model_type: str
+    model: Qwen3NextModel
+    lm_head: nn.Linear
+
+    def __init__(self, args: Any) -> None: ...
+    def __call__(
+        self,
+        inputs: mx.array,
+        cache: Optional[Any] = None,
+    ) -> mx.array: ...
+    def sanitize(self, weights: dict[str, Any]) -> dict[str, Any]: ...
+    @property
+    def layers(self) -> list[Qwen3NextDecoderLayer]: ...

.mlx_typings/mlx_lm/models/step3p5.pyi

@@ -0,0 +1,151 @@
+from dataclasses import dataclass
+from typing import Any, Dict, List, Optional
+
+import mlx.core as mx
+import mlx.nn as nn
+
+from .base import BaseModelArgs
+from .switch_layers import SwitchGLU
+
+@dataclass
+class ModelArgs(BaseModelArgs):
+    model_type: str
+    hidden_size: int
+    num_hidden_layers: int
+    vocab_size: int
+    num_attention_heads: int
+    num_attention_groups: int
+    head_dim: int
+    intermediate_size: int
+    rms_norm_eps: float
+    rope_theta: float
+    rope_scaling: Optional[Dict[str, Any]]
+    max_position_embeddings: int
+    sliding_window: int
+    layer_types: Optional[List[str]]
+    yarn_only_types: Optional[List[str]]
+    partial_rotary_factors: Optional[List[float]]
+    attention_other_setting: Optional[Dict[str, Any]]
+    use_head_wise_attn_gate: bool
+    moe_num_experts: int
+    moe_top_k: int
+    moe_intermediate_size: int
+    share_expert_dim: int
+    moe_layers_enum: Optional[str]
+    moe_router_scaling_factor: float
+    norm_expert_weight: bool
+    swiglu_limits: Optional[List[float]]
+    swiglu_limits_shared: Optional[List[float]]
+    tie_word_embeddings: bool
+
+class Step3p5MLP(nn.Module):
+    hidden_size: int
+    intermediate_size: int
+    gate_proj: nn.Linear
+    up_proj: nn.Linear
+    down_proj: nn.Linear
+    limit: Optional[float]
+
+    def __init__(
+        self, args: ModelArgs, intermediate_size: int, swiglu_limit: float = 0
+    ) -> None: ...
+    def __call__(self, x: mx.array) -> mx.array: ...
+
+class Step3p5MoEGate(nn.Module):
+    top_k: int
+    n_routed_experts: int
+    routed_scaling_factor: float
+    norm_topk_prob: bool
+    gate: nn.Linear
+    router_bias: mx.array
+
+    def __init__(self, args: ModelArgs) -> None: ...
+    def __call__(self, x: mx.array) -> tuple[mx.array, mx.array]: ...
+
+class Step3p5MoE(nn.Module):
+    gate: Step3p5MoEGate
+    switch_mlp: SwitchGLU
+    share_expert: Step3p5MLP
+    sharding_group: Optional[mx.distributed.Group]
+
+    def __init__(self, args: ModelArgs, layer_idx: int) -> None: ...
+    def __call__(self, x: mx.array) -> mx.array: ...
+
+class Step3p5Attention(nn.Module):
+    is_sliding: bool
+    num_heads: int
+    num_kv_heads: int
+    head_dim: int
+    scale: float
+    q_proj: nn.Linear
+    k_proj: nn.Linear
+    v_proj: nn.Linear
+    o_proj: nn.Linear
+    q_norm: nn.Module
+    k_norm: nn.Module
+    use_head_wise_attn_gate: bool
+    g_proj: nn.Linear
+    rope: nn.Module
+
+    def __init__(self, args: ModelArgs, layer_idx: int) -> None: ...
+    def __call__(
+        self,
+        x: mx.array,
+        mask: Optional[mx.array] = None,
+        cache: Optional[Any] = None,
+    ) -> mx.array: ...
+
+class Step3p5DecoderLayer(nn.Module):
+    self_attn: Step3p5Attention
+    is_sliding: bool
+    is_moe_layer: bool
+    mlp: Step3p5MLP | Step3p5MoE
+    input_layernorm: nn.Module
+    post_attention_layernorm: nn.Module
+
+    def __init__(self, args: ModelArgs, layer_idx: int) -> None: ...
+    def __call__(
+        self,
+        x: mx.array,
+        mask: Optional[mx.array] = None,
+        cache: Optional[Any] = None,
+    ) -> mx.array: ...
+
+class Step3p5Model(nn.Module):
+    args: ModelArgs
+    vocab_size: int
+    num_layers: int
+    embed_tokens: nn.Embedding
+    layers: list[Step3p5DecoderLayer]
+    norm: nn.Module
+    _swa_idx: Optional[int]
+    _full_idx: Optional[int]
+
+    def __init__(self, args: ModelArgs) -> None: ...
+    def __call__(
+        self,
+        x: mx.array,
+        cache: Optional[List[Any]] = None,
+    ) -> mx.array: ...
+
+class Model(nn.Module):
+    args: ModelArgs
+    model_type: str
+    model: Step3p5Model
+    lm_head: nn.Linear
+
+    def __init__(self, args: ModelArgs) -> None: ...
+    def __call__(
+        self,
+        inputs: mx.array,
+        cache: Optional[List[Any]] = None,
+    ) -> mx.array: ...
+    def sanitize(self, weights: dict[str, Any]) -> dict[str, Any]: ...
+    def shard(self, group: Optional[mx.distributed.Group] = None) -> None: ...
+    @property
+    def layers(self) -> list[Step3p5DecoderLayer]: ...
+    def make_cache(self) -> list[Any]: ...
+    @property
+    def cast_predicate(self) -> Any: ...
+    @property
+    def quant_predicate(self) -> Any: ...

.mlx_typings/mlx_lm/tokenizer_utils.pyi

@@ -108,16 +108,21 @@ class TokenizerWrapper:
     _tokenizer: PreTrainedTokenizerFast
     eos_token_id: int | None
     eos_token: str | None
+    eos_token_ids: list[int] | set[int] | None
     bos_token_id: int | None
     bos_token: str | None
     vocab_size: int
     all_special_tokens: list[str]
+    think_start: str | None
+    think_end: str | None
+    think_start_id: int | None
+    think_end_id: int | None
 
     def __init__(
         self,
         tokenizer: Any,
         detokenizer_class: Any = ...,
-        eos_token_ids: list[int] | None = ...,
+        eos_token_ids: list[int] | set[int] | None = ...,
         chat_template: Any = ...,
         tool_parser: Any = ...,
         tool_call_start: str | None = ...,

AGENTS.md

@@ -119,3 +119,78 @@ From .cursorrules:
 ## Testing
 
 Tests use pytest-asyncio with `asyncio_mode = "auto"`. Tests are in `tests/` subdirectories alongside the code they test. The `EXO_TESTS=1` env var is set during tests.
+
+## Dashboard UI Testing & Screenshots
+
+### Building and Running the Dashboard
+```bash
+# Build the dashboard (must be done before running exo)
+cd dashboard && npm install && npm run build && cd ..
+
+# Start exo (serves the dashboard at http://localhost:52415)
+uv run exo &
+sleep 8  # Wait for server to start
+```
+
+### Taking Headless Screenshots with Playwright
+Use Playwright with headless Chromium for programmatic screenshots — no manual browser interaction needed.
+
+**Setup (one-time):**
+```bash
+npx --yes playwright install chromium
+cd /tmp && npm init -y && npm install playwright
+```
+
+**Taking screenshots:**
+```javascript
+// Run from /tmp where playwright is installed: cd /tmp && node -e "..."
+const { chromium } = require('playwright');
+(async () => {
+  const browser = await chromium.launch({ headless: true });
+  const page = await browser.newPage({ viewport: { width: 1280, height: 800 } });
+  await page.goto('http://localhost:52415', { waitUntil: 'networkidle' });
+  await page.waitForTimeout(2000);
+
+  // Inject test data into localStorage if needed (e.g., recent models)
+  await page.evaluate(() => {
+    localStorage.setItem('exo-recent-models', JSON.stringify([
+      { modelId: 'mlx-community/Qwen3-30B-A3B-4bit', launchedAt: Date.now() },
+    ]));
+  });
+  await page.reload({ waitUntil: 'networkidle' });
+  await page.waitForTimeout(2000);
+
+  // Interact with UI elements
+  await page.locator('text=SELECT MODEL').click();
+  await page.waitForTimeout(1000);
+
+  // Take screenshot
+  await page.screenshot({ path: '/tmp/screenshot.png', fullPage: false });
+  await browser.close();
+})();
+```
+
+### Uploading Images to GitHub PRs
+GitHub's API doesn't support direct image upload for PR comments. Workaround:
+
+1. **Commit images to the branch** (temporarily):
+   ```bash
+   cp /tmp/screenshot.png .
+   git add screenshot.png
+   git commit -m "temp: add screenshots for PR"
+   git push origin <branch>
+   COMMIT_SHA=$(git rev-parse HEAD)
+   ```
+
+2. **Post PR comment** referencing the raw image URL (uses permanent commit SHA so images survive deletion):
+   ```bash
+   gh pr comment <PR_NUMBER> --body "![Screenshot](https://raw.githubusercontent.com/exo-explore/exo/${COMMIT_SHA}/screenshot.png)"
+   ```
+
+3. **Remove the images** from the branch:
+   ```bash
+   git rm screenshot.png
+   git commit -m "chore: remove temporary screenshot files"
+   git push origin <branch>
+   ```
+   The images still render in the PR comment because they reference the permanent commit SHA.

Cargo.lock

@@ -353,31 +353,6 @@ dependencies = [
  "generic-array",
 ]
 
-[[package]]
-name = "bon"
-version = "3.8.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ebeb9aaf9329dff6ceb65c689ca3db33dbf15f324909c60e4e5eef5701ce31b1"
-dependencies = [
- "bon-macros",
- "rustversion",
-]
-
-[[package]]
-name = "bon-macros"
-version = "3.8.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "77e9d642a7e3a318e37c2c9427b5a6a48aa1ad55dcd986f3034ab2239045a645"
-dependencies = [
- "darling",
- "ident_case",
- "prettyplease",
- "proc-macro2",
- "quote",
- "rustversion",
- "syn 2.0.111",
-]
-
 [[package]]
 name = "bs58"
 version = "0.5.1"
@@ -700,41 +675,6 @@ dependencies = [
  "syn 2.0.111",
 ]
 
-[[package]]
-name = "darling"
-version = "0.21.3"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9cdf337090841a411e2a7f3deb9187445851f91b309c0c0a29e05f74a00a48c0"
-dependencies = [
- "darling_core",
- "darling_macro",
-]
-
-[[package]]
-name = "darling_core"
-version = "0.21.3"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1247195ecd7e3c85f83c8d2a366e4210d588e802133e1e355180a9870b517ea4"
-dependencies = [
- "fnv",
- "ident_case",
- "proc-macro2",
- "quote",
- "strsim",
- "syn 2.0.111",
-]
-
-[[package]]
-name = "darling_macro"
-version = "0.21.3"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d38308df82d1080de0afee5d069fa14b0326a88c14f15c5ccda35b4a6c414c81"
-dependencies = [
- "darling_core",
- "quote",
- "syn 2.0.111",
-]
-
 [[package]]
 name = "data-encoding"
 version = "2.9.0"
@@ -1625,12 +1565,6 @@ dependencies = [
  "zerovec",
 ]
 
-[[package]]
-name = "ident_case"
-version = "1.0.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b9e0384b61958566e926dc50660321d12159025e767c18e043daf26b70104c39"
-
 [[package]]
 name = "idna"
 version = "1.1.0"
@@ -1745,15 +1679,6 @@ dependencies = [
  "generic-array",
 ]
 
-[[package]]
-name = "internment"
-version = "0.8.6"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "636d4b0f6a39fd684effe2a73f5310df16a3fa7954c26d36833e98f44d1977a2"
-dependencies = [
- "hashbrown 0.15.5",
-]
-
 [[package]]
 name = "inventory"
 version = "0.3.21"
@@ -3307,16 +3232,6 @@ dependencies = [
  "zerocopy",
 ]
 
-[[package]]
-name = "prettyplease"
-version = "0.2.37"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "479ca8adacdd7ce8f1fb39ce9ecccbfe93a3f1344b3d0d97f20bc0196208f62b"
-dependencies = [
- "proc-macro2",
- "syn 2.0.111",
-]
-
 [[package]]
 name = "primeorder"
 version = "0.13.6"
@@ -3740,12 +3655,6 @@ dependencies = [
  "yasna",
 ]
 
-[[package]]
-name = "recursion"
-version = "0.5.4"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9dba2197bf7b1d87b4dd460c195f4edeb45a94e82e8054f8d5f317c1f0e93ca1"
-
 [[package]]
 name = "redox_syscall"
 version = "0.5.18"
@@ -4807,15 +4716,6 @@ checksum = "06abde3611657adf66d383f00b093d7faecc7fa57071cce2578660c9f1010821"
 [[package]]
 name = "util"
 version = "0.0.1"
-dependencies = [
- "bon",
- "derive_more",
- "extend",
- "internment",
- "once_cell",
- "recursion",
- "thiserror 2.0.17",
-]
 
 [[package]]
 name = "uuid"

MISSED_THINGS.md

@@ -5,21 +5,21 @@
 [X] Fetching download status of all models on start
 [X] Deduplication of tasks in plan_step.
 [X] resolve_allow_patterns should just be wildcard now.
-[] no mx_barrier in genreate.py mlx_generate at the end.
+[X] no mx_barrier in genreate.py mlx_generate at the end.
 [] cache assertion not needed in auto_parallel.py PipelineLastLayer.
-[] GPTOSS support dropped in auto_parallel.py.
-[] sharding changed "all-to-sharded" became _all_to_sharded in auto_parallel.py.
-[] same as above with "sharded-to-all" became _sharded_to_all in auto_parallel.py.
-[] Dropped support for Ministral3Model, DeepseekV32Model, Glm4MoeModel, Qwen3NextModel, GptOssMode in auto_parallel.py.
+[X] GPTOSS support dropped in auto_parallel.py.
+[X] sharding changed "all-to-sharded" became _all_to_sharded in auto_parallel.py.
+[X] same as above with "sharded-to-all" became _sharded_to_all in auto_parallel.py.
+[X] Dropped support for Ministral3Model, DeepseekV32Model, Glm4MoeModel, Qwen3NextModel, GptOssMode in auto_parallel.py.
 [] Dropped prefill/decode code in auto_parallel.py and utils_mlx.py.
 [X] KV_CACHE_BITS should be None to disable quantized KV cache.
-[] Dropped _set_nofile_limit in utils_mlx.py.
-[] We have group optional in load_mlx_items in utils_mlx.py.
-[] Dropped add_missing_chat_templates for GptOss in load_mlx_items in utils_mlx.py.
-[] Dropped model.make_cache in make_kv_cache in utils_mlx.py.
+[X] Dropped _set_nofile_limit in utils_mlx.py.
+[X] We have group optional in load_mlx_items in utils_mlx.py.
+[X] Dropped add_missing_chat_templates for GptOss in load_mlx_items in utils_mlx.py.
+[X] Dropped model.make_cache in make_kv_cache in utils_mlx.py.
 [X] We put cache limit back in utils_mlx.py.
-[] topology.py remove_node removes the connections after checking if node is is in self._node_id_to_rx_id_map. on beta_1 it checks after, so would remove stale connections I guess?
-[] Missing Glm 4.7 model cards (this isn't ready yet but should be picked up, probably create an issue... the blocker is transforemrs version doesn't support the tokenizer for Glm 4.7. rc-1 does but we can't upgrade as it breaks other things.)
+[X] topology.py remove_node removes the connections after checking if node is is in self._node_id_to_rx_id_map. on beta_1 it checks after, so would remove stale connections I guess?
+[X] Missing Glm 4.7 model cards (this isn't ready yet but should be picked up, probably create an issue... the blocker is transforemrs version doesn't support the tokenizer for Glm 4.7. rc-1 does but we can't upgrade as it breaks other things.)
 [] try-except in _command_processor only excepts ValueError. This was silently failing leading to un-debuggable errors (we had a KeyError that was happening ). Changed this to catch Exception instead of ValueError. See exo-v2 89ae38405e0052e3c22405daf094b065878aa873 and fb99fea69b5a39017efc90c5dad0072e677455f0.
 [X] In placement.py, place_instance no longer looks at model_meta.supports_tensor and check if this tensor parallel number of nodes is supported by the model's tensor dimensions.
 [X] In placement.py, place_instanec, we no longer have the special case to exclude DeepSeek v3.1 pipeline parallel (it doesn't work).

TODO.md

@@ -1,28 +1,14 @@
-2. Currently a lot of requests from the API are timing out, but we still process those requests internally. If an API request times out, we should cancel all corresponding tasks to that API request (why process a request with nobody listening).
 3. Task cancellation. When API http request gets cancelled, it should cancel corresponding task.
 4. I'd like to see profiled network latency / bandwidth.
 5. I'd like to see how much bandwidth each link is using.
-6. We should handle the case where one machine doesn't have the model downloaded and then other machines are waiting on it. In this case we get loads of timeout errors because the others are waiting for the one that needs to download the model.
 7. Solve the problem of in continuous batching when a new prompt comes in, it will block decode of the current batch until the prefill is complete.
 8. We want people to be able to copy models over to a new device without ever connecting EXO to the internet. Right now EXO require internet connection once to cache some files to check if a download is complete. Instead, we should simply check if there is a non-empty model folder locally with no .partial files. This indicates it's a fully downloaded model that can be loaded.
-10. More granular control over how to deploy instances.
-12. Nix is great but installing it is a pain and we have ended up in a lot of cases having PATH issues or installation issues. For example, after rebooting mike it seemed to no longer have a nix installation and needed reinstalling. It has a bunch of broken symlinks left over from nix that caused ssh to fail, making it even harder to debug. We need consistent environments (perhaps MDM) so we can guarantee nix is installed properly on each machine.
 13. Memory pressure instead of memory used.
 14. Show the type of each connection (TB5, Ethernet, etc.) in the UI. Refer to old exo: https://github.com/exo-explore/exo/blob/56f783b38dc6b08ce606b07a5386dc40dae00330/exo/helpers.py#L251
 15. Prioritise certain connection types (or by latency). TB5 > Ethernet > WiFi. Refer to old exo: https://github.com/exo-explore/exo/blob/56f783b38dc6b08ce606b07a5386dc40dae00330/exo/helpers.py#L251
 16. Dynamically switch to higher priority connection when it becomes available. Probably bring back InstanceReplacedAtomically.
 17. Faster model loads by streaming model from other devices in cluster.
 18. Add support for specifying the type of network connection to use in a test. Depends on 15/16.
-20. Add chat completion cancellations (e.g OpenWebUI has something for cancelling an ongoing request).
-23. Do we need cache_limit? We went back and forth on that a lot because we thought it might be causing issues. One problem is it sets it relative to model size. So if you have multiple models loaded in it will take the most recent model size for the cache_limit. This is problematic if you launch DeepSeek -> Llama for example.
-24. further openai/lmstudio api compatibility
 25. Rethink retry logic
-26. Task cancellation. When API http request gets cancelled, it should cancel corresponding task.
 27. Log cleanup - per-module log filters and default to DEBUG log levels
 28. Validate RDMA connections with ibv_devinfo in the info gatherer
-
-Potential refactors:
-
-2. Topology can be simplified
-
-Random errors we've run into:

app/EXO/EXO/ContentView.swift

@@ -563,21 +563,45 @@ struct ContentView: View {
     }
 
     private var rdmaStatusView: some View {
-        let rdma = networkStatusService.status.rdmaStatus
+        let rdmaStatuses = stateService.latestSnapshot?.nodeRdmaCtl ?? [:]
+        let localNodeId = stateService.localNodeId
+        let nodeProfiles = stateService.latestSnapshot?.nodeProfiles ?? [:]
+        let localDevices = networkStatusService.status.localRdmaDevices
+        let localPorts = networkStatusService.status.localRdmaActivePorts
+
         return VStack(alignment: .leading, spacing: 1) {
-            Text("RDMA: \(rdmaStatusText(rdma))")
-                .font(.caption2)
-                .foregroundColor(rdmaStatusColor(rdma))
-            if !rdma.devices.isEmpty {
-                Text("  Devices: \(rdma.devices.joined(separator: ", "))")
+            if rdmaStatuses.isEmpty {
+                Text("Cluster RDMA: No data")
+                    .font(.caption2)
+                    .foregroundColor(.secondary)
+            } else {
+                Text("Cluster RDMA Status:")
+                    .font(.caption2)
+                    .foregroundColor(.secondary)
+                ForEach(Array(rdmaStatuses.keys.sorted()), id: \.self) { nodeId in
+                    if let status = rdmaStatuses[nodeId] {
+                        let nodeName =
+                            nodeProfiles[nodeId]?.friendlyName ?? String(nodeId.prefix(8))
+                        let isLocal = nodeId == localNodeId
+                        let prefix = isLocal ? "  \(nodeName) (local):" : "  \(nodeName):"
+                        let statusText = status.enabled ? "Enabled" : "Disabled"
+                        let color: Color = status.enabled ? .green : .orange
+                        Text("\(prefix) \(statusText)")
+                            .font(.caption2)
+                            .foregroundColor(color)
+                    }
+                }
+            }
+            if !localDevices.isEmpty {
+                Text("  Local Devices: \(localDevices.joined(separator: ", "))")
                     .font(.caption2)
                     .foregroundColor(.secondary)
             }
-            if !rdma.activePorts.isEmpty {
-                Text("  Active Ports:")
+            if !localPorts.isEmpty {
+                Text("  Local Active Ports:")
                     .font(.caption2)
                     .foregroundColor(.secondary)
-                ForEach(rdma.activePorts, id: \.device) { port in
+                ForEach(localPorts, id: \.device) { port in
                     Text("    \(port.device) port \(port.port): \(port.state)")
                         .font(.caption2)
                         .foregroundColor(.green)
@@ -586,28 +610,6 @@ struct ContentView: View {
         }
     }
 
-    private func rdmaStatusText(_ rdma: RDMAStatus) -> String {
-        switch rdma.rdmaCtlEnabled {
-        case .some(true):
-            return "Enabled"
-        case .some(false):
-            return "Disabled"
-        case nil:
-            return rdma.devices.isEmpty ? "Not Available" : "Available"
-        }
-    }
-
-    private func rdmaStatusColor(_ rdma: RDMAStatus) -> Color {
-        switch rdma.rdmaCtlEnabled {
-        case .some(true):
-            return .green
-        case .some(false):
-            return .orange
-        case nil:
-            return rdma.devices.isEmpty ? .secondary : .green
-        }
-    }
-
     private var sendBugReportButton: some View {
         VStack(alignment: .leading, spacing: 4) {
             Button {

app/EXO/EXO/EXOApp.swift

@@ -14,7 +14,6 @@ import SwiftUI
 import UserNotifications
 import os.log
 
-@main
 struct EXOApp: App {
     @StateObject private var controller: ExoProcessController
     @StateObject private var stateService: ClusterStateService

app/EXO/EXO/ExoProcessController.swift

@@ -28,6 +28,10 @@ final class ExoProcessController: ObservableObject {
         }
     }
 
+    static let exoDirectoryURL: URL = {
+        URL(fileURLWithPath: NSHomeDirectory()).appendingPathComponent(".exo")
+    }()
+
     @Published private(set) var status: Status = .stopped
     @Published private(set) var lastError: String?
     @Published private(set) var launchCountdownSeconds: Int?
@@ -78,7 +82,11 @@ final class ExoProcessController: ObservableObject {
 
             let child = Process()
             child.executableURL = executableURL
-            child.currentDirectoryURL = runtimeURL
+            let exoHomeURL = Self.exoDirectoryURL
+            try? FileManager.default.createDirectory(
+                at: exoHomeURL, withIntermediateDirectories: true
+            )
+            child.currentDirectoryURL = exoHomeURL
             child.environment = makeEnvironment(for: runtimeURL)
 
             child.standardOutput = FileHandle.nullDevice

app/EXO/EXO/Models/ClusterState.swift

@@ -15,6 +15,7 @@ struct ClusterState: Decodable {
     let nodeMemory: [String: MemoryInfo]
     let nodeSystem: [String: SystemInfo]
     let nodeThunderboltBridge: [String: ThunderboltBridgeStatus]
+    let nodeRdmaCtl: [String: NodeRdmaCtlStatus]
 
     /// Computed property for backwards compatibility - merges granular state into NodeProfile
     var nodeProfiles: [String: NodeProfile] {
@@ -65,6 +66,10 @@ struct ClusterState: Decodable {
             try container.decodeIfPresent(
                 [String: ThunderboltBridgeStatus].self, forKey: .nodeThunderboltBridge
             ) ?? [:]
+        self.nodeRdmaCtl =
+            try container.decodeIfPresent(
+                [String: NodeRdmaCtlStatus].self, forKey: .nodeRdmaCtl
+            ) ?? [:]
     }
 
     private enum CodingKeys: String, CodingKey {
@@ -78,6 +83,7 @@ struct ClusterState: Decodable {
         case nodeMemory
         case nodeSystem
         case nodeThunderboltBridge
+        case nodeRdmaCtl
     }
 }
 
@@ -159,6 +165,10 @@ struct ThunderboltBridgeStatus: Decodable {
     let serviceName: String?
 }
 
+struct NodeRdmaCtlStatus: Decodable {
+    let enabled: Bool
+}
+
 struct MemoryInfo: Decodable {
     let ramTotal: MemoryValue?
     let ramAvailable: MemoryValue?

app/EXO/EXO/Services/BugReportService.swift

@@ -44,16 +44,12 @@ struct BugReportService {
         let dayPrefix = Self.dayPrefixString(now)
         let prefix = "reports/\(dayPrefix)/\(timestamp)/"
 
-        let logData = readLog()
+        let logFiles = readAllLogs()
         let ifconfigText = try await captureIfconfig()
         let hostName = Host.current().localizedName ?? "unknown"
         let debugInfo = readDebugInfo()
 
-        async let stateResult = fetch(url: baseURL.appendingPathComponent("state"))
-        async let eventsResult = fetch(url: baseURL.appendingPathComponent("events"))
-
-        let stateData = try await stateResult
-        let eventsData = try await eventsResult
+        let stateData = try await fetch(url: baseURL.appendingPathComponent("state"))
 
         // Extract cluster TB bridge status from exo state
         let clusterTbBridgeStatus = extractClusterTbBridgeStatus(from: stateData)
@@ -67,12 +63,19 @@ struct BugReportService {
             clusterTbBridgeStatus: clusterTbBridgeStatus
         )
 
-        let uploads: [(path: String, data: Data?)] = [
-            ("\(prefix)exo.log", logData),
+        let eventLogFiles = readAllEventLogs()
+
+        var uploads: [(path: String, data: Data?)] = logFiles.map { (path, data) in
+            ("\(prefix)\(path)", data)
+        }
+        uploads.append(
+            contentsOf: eventLogFiles.map { (path, data) in
+                ("\(prefix)\(path)", data as Data?)
+            })
+        uploads.append(contentsOf: [
             ("\(prefix)state.json", stateData),
-            ("\(prefix)events.json", eventsData),
             ("\(prefix)report.json", reportJSON),
-        ]
+        ])
 
         let uploadItems: [(key: String, body: Data)] = uploads.compactMap { item in
             guard let body = item.data else { return nil }
@@ -149,11 +152,40 @@ struct BugReportService {
         return decoded.urls
     }
 
-    private func readLog() -> Data? {
-        let logURL = URL(fileURLWithPath: NSHomeDirectory())
+    private func readAllLogs() -> [(path: String, data: Data)] {
+        let dir = URL(fileURLWithPath: NSHomeDirectory())
             .appendingPathComponent(".exo")
-            .appendingPathComponent("exo.log")
-        return try? Data(contentsOf: logURL)
+            .appendingPathComponent("exo_log")
+        var results: [(path: String, data: Data)] = []
+
+        let contents = (try? FileManager.default.contentsOfDirectory(atPath: dir.path)) ?? []
+        for name in contents {
+            if let data = try? Data(contentsOf: dir.appendingPathComponent(name)) {
+                results.append(("exo_log/\(name)", data))
+            }
+        }
+
+        return results
+    }
+
+    private func readAllEventLogs() -> [(path: String, data: Data)] {
+        let eventLogDir = URL(fileURLWithPath: NSHomeDirectory())
+            .appendingPathComponent(".exo")
+            .appendingPathComponent("event_log")
+        var results: [(path: String, data: Data)] = []
+
+        for subdir in ["master", "api"] {
+            let dir = eventLogDir.appendingPathComponent(subdir)
+            let contents =
+                (try? FileManager.default.contentsOfDirectory(atPath: dir.path)) ?? []
+            for name in contents where name.hasPrefix("events.") {
+                if let data = try? Data(contentsOf: dir.appendingPathComponent(name)) {
+                    results.append(("event_log/\(subdir)/\(name)", data))
+                }
+            }
+        }
+
+        return results
     }
 
     private func captureIfconfig() async throws -> String {

app/EXO/EXO/Services/NetworkSetupHelper.swift

@@ -288,6 +288,61 @@ enum NetworkSetupHelper {
         """
     }
 
+    /// Direct install without GUI (requires root).
+    /// Returns true on success, false on failure.
+    static func installDirectly() -> Bool {
+        let script = makeInstallerScript()
+        return runShellDirectly(script)
+    }
+
+    /// Direct uninstall without GUI (requires root).
+    /// Returns true on success, false on failure.
+    static func uninstallDirectly() -> Bool {
+        let script = makeUninstallScript()
+        return runShellDirectly(script)
+    }
+
+    /// Run a shell script directly via Process (no AppleScript, requires root).
+    /// Returns true on success, false on failure.
+    private static func runShellDirectly(_ script: String) -> Bool {
+        let process = Process()
+        process.executableURL = URL(fileURLWithPath: "/bin/bash")
+        process.arguments = ["-c", script]
+
+        let outputPipe = Pipe()
+        let errorPipe = Pipe()
+        process.standardOutput = outputPipe
+        process.standardError = errorPipe
+
+        do {
+            try process.run()
+            process.waitUntilExit()
+
+            let outputData = outputPipe.fileHandleForReading.readDataToEndOfFile()
+            let errorData = errorPipe.fileHandleForReading.readDataToEndOfFile()
+
+            if let output = String(data: outputData, encoding: .utf8), !output.isEmpty {
+                print(output)
+            }
+            if let errorOutput = String(data: errorData, encoding: .utf8), !errorOutput.isEmpty {
+                fputs(errorOutput, stderr)
+            }
+
+            if process.terminationStatus == 0 {
+                logger.info("Shell script completed successfully")
+                return true
+            } else {
+                logger.error("Shell script failed with exit code \(process.terminationStatus)")
+                return false
+            }
+        } catch {
+            logger.error(
+                "Failed to run shell script: \(error.localizedDescription, privacy: .public)")
+            fputs("Error: \(error.localizedDescription)\n", stderr)
+            return false
+        }
+    }
+
     private static func runShellAsAdmin(_ script: String) throws {
         let escapedScript =
             script

app/EXO/EXO/Services/NetworkStatusService.swift

@@ -35,28 +35,18 @@ struct NetworkStatus: Equatable {
     let thunderboltBridgeState: ThunderboltState?
     let bridgeInactive: Bool?
     let interfaceStatuses: [InterfaceIpStatus]
-    let rdmaStatus: RDMAStatus
+    let localRdmaDevices: [String]
+    let localRdmaActivePorts: [RDMAPort]
 
     static let empty = NetworkStatus(
         thunderboltBridgeState: nil,
         bridgeInactive: nil,
         interfaceStatuses: [],
-        rdmaStatus: .empty
+        localRdmaDevices: [],
+        localRdmaActivePorts: []
     )
 }
 
-struct RDMAStatus: Equatable {
-    let rdmaCtlEnabled: Bool?
-    let devices: [String]
-    let activePorts: [RDMAPort]
-
-    var isAvailable: Bool {
-        rdmaCtlEnabled == true || !devices.isEmpty
-    }
-
-    static let empty = RDMAStatus(rdmaCtlEnabled: nil, devices: [], activePorts: [])
-}
-
 struct RDMAPort: Equatable {
     let device: String
     let port: String
@@ -80,31 +70,11 @@ private struct NetworkStatusFetcher {
             thunderboltBridgeState: readThunderboltBridgeState(),
             bridgeInactive: readBridgeInactive(),
             interfaceStatuses: readInterfaceStatuses(),
-            rdmaStatus: readRDMAStatus()
+            localRdmaDevices: readRDMADevices(),
+            localRdmaActivePorts: readRDMAActivePorts()
         )
     }
 
-    private func readRDMAStatus() -> RDMAStatus {
-        let rdmaCtlEnabled = readRDMACtlEnabled()
-        let devices = readRDMADevices()
-        let activePorts = readRDMAActivePorts()
-        return RDMAStatus(
-            rdmaCtlEnabled: rdmaCtlEnabled, devices: devices, activePorts: activePorts)
-    }
-
-    private func readRDMACtlEnabled() -> Bool? {
-        let result = runCommand(["rdma_ctl", "status"])
-        guard result.exitCode == 0 else { return nil }
-        let output = result.output.lowercased().trimmingCharacters(in: .whitespacesAndNewlines)
-        if output.contains("enabled") {
-            return true
-        }
-        if output.contains("disabled") {
-            return false
-        }
-        return nil
-    }
-
     private func readRDMADevices() -> [String] {
         let result = runCommand(["ibv_devices"])
         guard result.exitCode == 0 else { return [] }

app/EXO/EXO/ViewModels/InstanceViewModel.swift

@@ -216,7 +216,7 @@ struct InstanceTaskViewModel: Identifiable, Equatable {
     let promptPreview: String?
     let errorMessage: String?
     let subtitle: String?
-    let parameters: ChatCompletionTaskParameters?
+    let parameters: TextGenerationTaskParameters?
 
     var title: String {
         switch kind {

app/EXO/EXO/main.swift

@@ -0,0 +1,85 @@
+//
+//  main.swift
+//  EXO
+//
+//  Created by Jake Hillion on 2026-02-03.
+//
+
+import Foundation
+
+/// Command line options for the EXO app
+enum CLICommand {
+    case install
+    case uninstall
+    case help
+    case none
+}
+
+/// Parse command line arguments to determine the CLI command
+func parseArguments() -> CLICommand {
+    let args = CommandLine.arguments
+    if args.contains("--help") || args.contains("-h") {
+        return .help
+    }
+    if args.contains("--install") {
+        return .install
+    }
+    if args.contains("--uninstall") {
+        return .uninstall
+    }
+    return .none
+}
+
+/// Print usage information
+func printUsage() {
+    let programName = (CommandLine.arguments.first as NSString?)?.lastPathComponent ?? "EXO"
+    print(
+        """
+        Usage: \(programName) [OPTIONS]
+
+        Options:
+          --install     Install EXO network configuration (requires root)
+          --uninstall   Uninstall EXO network configuration (requires root)
+          --help, -h    Show this help message
+
+        When run without options, starts the normal GUI application.
+
+        Examples:
+          sudo \(programName) --install    Install network components as root
+          sudo \(programName) --uninstall  Remove network components as root
+        """)
+}
+
+/// Check if running as root
+func isRunningAsRoot() -> Bool {
+    return getuid() == 0
+}
+
+// Main entry point
+let command = parseArguments()
+
+switch command {
+case .help:
+    printUsage()
+    exit(0)
+
+case .install:
+    if !isRunningAsRoot() {
+        fputs("Error: --install requires root privileges. Run with sudo.\n", stderr)
+        exit(1)
+    }
+    let success = NetworkSetupHelper.installDirectly()
+    exit(success ? 0 : 1)
+
+case .uninstall:
+    if !isRunningAsRoot() {
+        fputs("Error: --uninstall requires root privileges. Run with sudo.\n", stderr)
+        exit(1)
+    }
+    let success = NetworkSetupHelper.uninstallDirectly()
+    exit(success ? 0 : 1)
+
+case .none:
+    // Start normal GUI application
+    EXOApp.main()
+}

bench/exo_bench.py

@@ -19,6 +19,11 @@ from urllib.parse import urlencode
 from loguru import logger
 from transformers import AutoTokenizer
 
+# Backoff constants for cluster settling retry
+_SETTLE_INITIAL_BACKOFF_S = 1.0
+_SETTLE_MAX_BACKOFF_S = 60.0
+_SETTLE_BACKOFF_MULTIPLIER = 2.0
+
 # Monkey-patch for transformers 5.x compatibility
 # Kimi's tokenization_kimi.py imports bytes_to_unicode from the old location
 # which was moved in transformers 5.0.0rc2
@@ -283,6 +288,151 @@ def resolve_model_short_id(client: ExoClient, model_arg: str) -> tuple[str, str]
     raise ValueError(f"Model not found in /models: {model_arg}")
 
 
+def run_planning_phase(
+    client: ExoClient,
+    full_model_id: str,
+    preview: dict[str, Any],
+    danger_delete: bool,
+    timeout: float,
+    settle_deadline: float | None,
+) -> None:
+    """Check disk space and ensure model is downloaded before benchmarking."""
+    # Get model size from /models
+    models = client.request_json("GET", "/models") or {}
+    model_bytes = 0
+    for m in models.get("data", []):
+        if m.get("hugging_face_id") == full_model_id:
+            model_bytes = m.get("storage_size_megabytes", 0) * 1024 * 1024
+            break
+
+    if not model_bytes:
+        logger.warning(
+            f"Could not determine size for {full_model_id}, skipping disk check"
+        )
+        return
+
+    # Get nodes from preview
+    inner = unwrap_instance(preview["instance"])
+    node_ids = list(inner["shardAssignments"]["nodeToRunner"].keys())
+    runner_to_shard = inner["shardAssignments"]["runnerToShard"]
+
+    state = client.request_json("GET", "/state")
+    downloads = state.get("downloads", {})
+    node_disk = state.get("nodeDisk", {})
+
+    for node_id in node_ids:
+        node_downloads = downloads.get(node_id, [])
+
+        # Check if model already downloaded on this node
+        already_downloaded = any(
+            "DownloadCompleted" in p
+            and unwrap_instance(p["DownloadCompleted"]["shardMetadata"])["modelCard"][
+                "modelId"
+            ]
+            == full_model_id
+            for p in node_downloads
+        )
+        if already_downloaded:
+            continue
+
+        # Wait for disk info if settle_deadline is set
+        disk_info = node_disk.get(node_id, {})
+        backoff = _SETTLE_INITIAL_BACKOFF_S
+        while not disk_info and settle_deadline and time.monotonic() < settle_deadline:
+            remaining = settle_deadline - time.monotonic()
+            logger.info(
+                f"Waiting for disk info on {node_id} ({remaining:.0f}s remaining)..."
+            )
+            time.sleep(min(backoff, remaining))
+            backoff = min(backoff * _SETTLE_BACKOFF_MULTIPLIER, _SETTLE_MAX_BACKOFF_S)
+            state = client.request_json("GET", "/state")
+            node_disk = state.get("nodeDisk", {})
+            disk_info = node_disk.get(node_id, {})
+
+        if not disk_info:
+            logger.warning(f"No disk info for {node_id}, skipping space check")
+            continue
+
+        avail = disk_info.get("available", {}).get("inBytes", 0)
+        if avail >= model_bytes:
+            continue
+
+        if not danger_delete:
+            raise RuntimeError(
+                f"Insufficient disk on {node_id}: need {model_bytes // (1024**3)}GB, "
+                f"have {avail // (1024**3)}GB. Use --danger-delete-downloads to free space."
+            )
+
+        # Delete from smallest to largest
+        completed = [
+            (
+                unwrap_instance(p["DownloadCompleted"]["shardMetadata"])["modelCard"][
+                    "modelId"
+                ],
+                p["DownloadCompleted"]["totalBytes"]["inBytes"],
+            )
+            for p in node_downloads
+            if "DownloadCompleted" in p
+        ]
+        for del_model, size in sorted(completed, key=lambda x: x[1]):
+            logger.info(f"Deleting {del_model} from {node_id} ({size // (1024**2)}MB)")
+            client.request_json("DELETE", f"/download/{node_id}/{del_model}")
+            avail += size
+            if avail >= model_bytes:
+                break
+
+        if avail < model_bytes:
+            raise RuntimeError(f"Could not free enough space on {node_id}")
+
+    # Start downloads (idempotent)
+    for node_id in node_ids:
+        runner_id = inner["shardAssignments"]["nodeToRunner"][node_id]
+        shard = runner_to_shard[runner_id]
+        client.request_json(
+            "POST",
+            "/download/start",
+            body={
+                "targetNodeId": node_id,
+                "shardMetadata": shard,
+            },
+        )
+        logger.info(f"Started download on {node_id}")
+
+    # Wait for downloads
+    start = time.time()
+    while time.time() - start < timeout:
+        state = client.request_json("GET", "/state")
+        downloads = state.get("downloads", {})
+        all_done = True
+        for node_id in node_ids:
+            done = any(
+                "DownloadCompleted" in p
+                and unwrap_instance(p["DownloadCompleted"]["shardMetadata"])[
+                    "modelCard"
+                ]["modelId"]
+                == full_model_id
+                for p in downloads.get(node_id, [])
+            )
+            failed = [
+                p["DownloadFailed"]["errorMessage"]
+                for p in downloads.get(node_id, [])
+                if "DownloadFailed" in p
+                and unwrap_instance(p["DownloadFailed"]["shardMetadata"])["modelCard"][
+                    "modelId"
+                ]
+                == full_model_id
+            ]
+            if failed:
+                raise RuntimeError(f"Download failed on {node_id}: {failed[0]}")
+            if not done:
+                all_done = False
+        if all_done:
+            return
+        time.sleep(1)
+
+    raise TimeoutError("Downloads did not complete in time")
+
+
 def placement_filter(instance_meta: str, wanted: str) -> bool:
     s = (instance_meta or "").lower()
     if wanted == "both":
@@ -388,6 +538,66 @@ class PromptSizer:
         return content, tok
 
 
+def fetch_and_filter_placements(
+    client: ExoClient, full_model_id: str, args: argparse.Namespace
+) -> list[dict[str, Any]]:
+    previews_resp = client.request_json(
+        "GET", "/instance/previews", params={"model_id": full_model_id}
+    )
+    previews = previews_resp.get("previews") or []
+
+    selected: list[dict[str, Any]] = []
+    for p in previews:
+        if p.get("error") is not None:
+            continue
+        if not placement_filter(str(p.get("instance_meta", "")), args.instance_meta):
+            continue
+        if not sharding_filter(str(p.get("sharding", "")), args.sharding):
+            continue
+
+        instance = p.get("instance")
+        if not isinstance(instance, dict):
+            continue
+
+        n = nodes_used_in_instance(instance)
+        # Skip tensor ring single node as it is pointless when pipeline ring
+        if n == 1 and (
+            (args.sharding == "both" and "tensor" in p.get("sharding", "").lower())
+            or (
+                args.instance_meta == "both"
+                and "jaccl" in p.get("instance_meta", "").lower()
+            )
+        ):
+            continue
+
+        if (
+            args.skip_pipeline_jaccl
+            and (
+                args.instance_meta == "both"
+                and "jaccl" in p.get("instance_meta", "").lower()
+            )
+            and (
+                args.sharding == "both" and "pipeline" in p.get("sharding", "").lower()
+            )
+        ):
+            continue
+
+        if (
+            args.skip_tensor_ring
+            and (
+                args.instance_meta == "both"
+                and "ring" in p.get("instance_meta", "").lower()
+            )
+            and (args.sharding == "both" and "tensor" in p.get("sharding", "").lower())
+        ):
+            continue
+
+        if args.min_nodes <= n <= args.max_nodes:
+            selected.append(p)
+
+    return selected
+
+
 def main() -> int:
     ap = argparse.ArgumentParser(
         prog="exo-bench",
@@ -431,7 +641,12 @@ def main() -> int:
     ap.add_argument(
         "--skip-pipeline-jaccl",
         action="store_true",
-        help="Pipeline jaccl is often pointless, skip by default",
+        help="Skip pipeline+jaccl placements, as it's often pointless.",
+    )
+    ap.add_argument(
+        "--skip-tensor-ring",
+        action="store_true",
+        help="Skip tensor+ring placements, as it's so slow.",
     )
     ap.add_argument(
         "--repeat", type=int, default=1, help="Repetitions per (pp,tg) pair."
@@ -450,6 +665,7 @@ def main() -> int:
         default="bench/results.json",
         help="Write raw per-run results JSON to this path.",
     )
+    ap.add_argument("--stdout", action="store_true", help="Write results to stdout")
     ap.add_argument(
         "--dry-run", action="store_true", help="List selected placements and exit."
     )
@@ -458,6 +674,17 @@ def main() -> int:
         action="store_true",
         help="Force all pp×tg combinations (cartesian product) even when lists have equal length.",
     )
+    ap.add_argument(
+        "--settle-timeout",
+        type=float,
+        default=0,
+        help="Max seconds to wait for the cluster to produce valid placements (0 = try once).",
+    )
+    ap.add_argument(
+        "--danger-delete-downloads",
+        action="store_true",
+        help="Delete existing models from smallest to largest to make room for benchmark model.",
+    )
     args = ap.parse_args()
 
     pp_list = parse_int_list(args.pp)
@@ -481,11 +708,6 @@ def main() -> int:
     client = ExoClient(args.host, args.port, timeout_s=args.timeout)
     short_id, full_model_id = resolve_model_short_id(client, args.model)
 
-    previews_resp = client.request_json(
-        "GET", "/instance/previews", params={"model_id": full_model_id}
-    )
-    previews = previews_resp.get("previews") or []
-
     tokenizer = load_tokenizer_for_bench(full_model_id)
     if tokenizer is None:
         raise RuntimeError("[exo-bench] tokenizer load failed")
@@ -497,44 +719,23 @@ def main() -> int:
         logger.error("[exo-bench] tokenizer usable but prompt sizing failed")
         raise
 
-    selected: list[dict[str, Any]] = []
-    for p in previews:
-        if p.get("error") is not None:
-            continue
-        if not placement_filter(str(p.get("instance_meta", "")), args.instance_meta):
-            continue
-        if not sharding_filter(str(p.get("sharding", "")), args.sharding):
-            continue
+    settle_deadline = (
+        time.monotonic() + args.settle_timeout if args.settle_timeout > 0 else None
+    )
 
-        instance = p.get("instance")
-        if not isinstance(instance, dict):
-            continue
+    selected = fetch_and_filter_placements(client, full_model_id, args)
 
-        n = nodes_used_in_instance(instance)
-        # Skip tensor ring single node as it is pointless when pipeline ring
-        if n == 1 and (
-            (args.sharding == "both" and "tensor" in p.get("sharding", "").lower())
-            or (
-                args.instance_meta == "both"
-                and "jaccl" in p.get("instance_meta", "").lower()
+    if not selected and settle_deadline:
+        backoff = _SETTLE_INITIAL_BACKOFF_S
+        while not selected and time.monotonic() < settle_deadline:
+            remaining = settle_deadline - time.monotonic()
+            logger.warning(
+                f"No valid placements yet (cluster may still be settling). "
+                f"Retrying in {backoff:.1f}s ({remaining:.0f}s remaining)..."
             )
-        ):
-            continue
-
-        if (
-            args.skip_pipeline_jaccl
-            and (
-                args.instance_meta == "both"
-                and "jaccl" in p.get("instance_meta", "").lower()
-            )
-            and (
-                args.sharding == "both" and "pipeline" in p.get("sharding", "").lower()
-            )
-        ):
-            continue
-
-        if args.min_nodes <= n <= args.max_nodes:
-            selected.append(p)
+            time.sleep(min(backoff, remaining))
+            backoff = min(backoff * _SETTLE_BACKOFF_MULTIPLIER, _SETTLE_MAX_BACKOFF_S)
+            selected = fetch_and_filter_placements(client, full_model_id, args)
 
     if not selected:
         logger.error("No valid placements matched your filters.")
@@ -559,6 +760,16 @@ def main() -> int:
     if args.dry_run:
         return 0
 
+    logger.info("Planning phase: checking downloads...")
+    run_planning_phase(
+        client,
+        full_model_id,
+        selected[0],
+        args.danger_delete_downloads,
+        args.timeout,
+        settle_deadline,
+    )
+
     all_rows: list[dict[str, Any]] = []
 
     for preview in selected:
@@ -652,7 +863,9 @@ def main() -> int:
 
             time.sleep(5)
 
-    if args.json_out:
+    if args.stdout:
+        json.dump(all_rows, sys.stdout, indent=2, ensure_ascii=False)
+    elif args.json_out:
         with open(args.json_out, "w", encoding="utf-8") as f:
             json.dump(all_rows, f, indent=2, ensure_ascii=False)
         logger.debug(f"\nWrote results JSON: {args.json_out}")

bench/pyproject.toml

@@ -0,0 +1,16 @@
+[project]
+name = "exo-bench"
+version = "0.1.0"
+description = "Benchmarking tool for exo distributed inference"
+requires-python = ">=3.13"
+dependencies = [
+    "loguru>=0.7.3",
+    "transformers>=5.0.0",
+    "huggingface-hub>=0.33.4",
+    "tiktoken>=0.12.0",
+    "jinja2>=3.1.0",
+]
+
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"

conftest.py

@@ -0,0 +1 @@
+collect_ignore = ["tests/start_distributed_test.py"]

dashboard/src/lib/components/ChatForm.svelte

@@ -12,6 +12,8 @@
     ttftMs,
     tps,
     totalTokens,
+    thinkingEnabled as thinkingEnabledStore,
+    setConversationThinking,
   } from "$lib/stores/app.svelte";
   import ChatAttachments from "./ChatAttachments.svelte";
   import ImageParamsPanel from "./ImageParamsPanel.svelte";
@@ -25,6 +27,7 @@
     autofocus?: boolean;
     showModelSelector?: boolean;
     modelTasks?: Record<string, string[]>;
+    modelCapabilities?: Record<string, string[]>;
   }
 
   let {
@@ -34,6 +37,7 @@
     autofocus = true,
     showModelSelector = false,
     modelTasks = {},
+    modelCapabilities = {},
   }: Props = $props();
 
   let message = $state("");
@@ -41,6 +45,7 @@
   let fileInputRef: HTMLInputElement | undefined = $state();
   let uploadedFiles = $state<ChatUploadedFile[]>([]);
   let isDragOver = $state(false);
+  const thinkingEnabled = $derived(thinkingEnabledStore());
   let loading = $derived(isLoading());
   const currentModel = $derived(selectedChatModel());
   const instanceData = $derived(instances());
@@ -95,6 +100,12 @@
     );
   });
 
+  const modelSupportsThinking = $derived(() => {
+    if (!currentModel) return false;
+    const caps = modelCapabilities[currentModel] || [];
+    return caps.includes("thinking") && caps.includes("text");
+  });
+
   const isEditOnlyWithoutImage = $derived(
     currentModel !== null &&
       modelSupportsOnlyImageEditing(currentModel) &&
@@ -254,6 +265,7 @@
 
   function handleSubmit() {
     if ((!message.trim() && uploadedFiles.length === 0) || loading) return;
+    if (isEditOnlyWithoutImage) return;
 
     const content = message.trim();
     const files = [...uploadedFiles];
@@ -278,11 +290,19 @@
       if (imageFile.preview) {
         editImage(content, imageFile.preview);
       }
-    } else if (isImageModel() && content) {
+    } else if (
+      currentModel &&
+      modelSupportsTextToImage(currentModel) &&
+      content
+    ) {
       // Use image generation for text-to-image models
       generateImage(content);
     } else {
-      sendMessage(content, files);
+      sendMessage(
+        content,
+        files,
+        modelSupportsThinking() ? thinkingEnabled : null,
+      );
     }
 
     // Refocus the textarea after sending
@@ -520,6 +540,35 @@
             </div>
           {/if}
         </div>
+        <!-- Thinking toggle -->
+        {#if modelSupportsThinking()}
+          <button
+            type="button"
+            onclick={() => setConversationThinking(!thinkingEnabled)}
+            class="flex items-center gap-1.5 px-2 py-1 rounded text-xs font-mono tracking-wide transition-all duration-200 flex-shrink-0 cursor-pointer border {thinkingEnabled
+              ? 'bg-exo-yellow/15 border-exo-yellow/40 text-exo-yellow'
+              : 'bg-exo-medium-gray/30 border-exo-medium-gray/50 text-exo-light-gray/60 hover:text-exo-light-gray'}"
+            title={thinkingEnabled
+              ? "Thinking enabled — click to disable"
+              : "Thinking disabled — click to enable"}
+          >
+            <svg
+              class="w-3.5 h-3.5"
+              viewBox="0 0 24 24"
+              fill="none"
+              stroke="currentColor"
+              stroke-width="1.5"
+            >
+              <path
+                d="M12 2a7 7 0 0 0-7 7c0 2.38 1.19 4.47 3 5.74V17a1 1 0 0 0 1 1h6a1 1 0 0 0 1-1v-2.26c1.81-1.27 3-3.36 3-5.74a7 7 0 0 0-7-7zM9 20h6M10 22h4"
+                stroke-linecap="round"
+                stroke-linejoin="round"
+              />
+            </svg>
+            <span>{thinkingEnabled ? "THINK" : "NO THINK"}</span>
+          </button>
+        {/if}
+
         <!-- Performance stats -->
         {#if currentTtft !== null || currentTps !== null}
           <div class="flex items-center gap-4 text-xs font-mono flex-shrink-0">
@@ -599,9 +648,8 @@
             : isImageModel()
               ? "Describe the image you want to generate..."
               : placeholder}
-        disabled={loading}
         rows={1}
-        class="flex-1 resize-none bg-transparent text-foreground placeholder:text-exo-light-gray/60 placeholder:text-sm placeholder:tracking-[0.15em] placeholder:leading-7 focus:outline-none focus:ring-0 focus:border-none disabled:opacity-50 text-sm leading-7 font-mono"
+        class="flex-1 resize-none bg-transparent text-foreground placeholder:text-exo-light-gray/60 placeholder:text-sm placeholder:tracking-[0.15em] placeholder:leading-7 focus:outline-none focus:ring-0 focus:border-none text-sm leading-7 font-mono"
         style="min-height: 28px; max-height: 150px;"
       ></textarea>
 

dashboard/src/lib/components/ChatMessages.svelte

@@ -6,11 +6,14 @@
     deleteMessage,
     editAndRegenerate,
     regenerateLastResponse,
+    regenerateFromToken,
     setEditingImage,
   } from "$lib/stores/app.svelte";
   import type { Message } from "$lib/stores/app.svelte";
   import type { MessageAttachment } from "$lib/stores/app.svelte";
   import MarkdownContent from "./MarkdownContent.svelte";
+  import TokenHeatmap from "./TokenHeatmap.svelte";
+  import ImageLightbox from "./ImageLightbox.svelte";
 
   interface Props {
     class?: string;
@@ -99,6 +102,26 @@
   let copiedMessageId = $state<string | null>(null);
   let expandedThinkingMessageIds = $state<Set<string>>(new Set());
 
+  // Lightbox state
+  let expandedImageSrc = $state<string | null>(null);
+
+  // Uncertainty heatmap toggle
+  let heatmapMessageIds = $state<Set<string>>(new Set());
+
+  function toggleHeatmap(messageId: string) {
+    const next = new Set(heatmapMessageIds);
+    if (next.has(messageId)) {
+      next.delete(messageId);
+    } else {
+      next.add(messageId);
+    }
+    heatmapMessageIds = next;
+  }
+
+  function isHeatmapVisible(messageId: string): boolean {
+    return heatmapMessageIds.has(messageId);
+  }
+
   function formatTimestamp(timestamp: number): string {
     return new Date(timestamp).toLocaleTimeString("en-US", {
       hour12: false,
@@ -202,6 +225,7 @@
   }
 
   function handleDeleteClick(messageId: string) {
+    if (loading) return;
     deleteConfirmId = messageId;
   }
 
@@ -232,7 +256,7 @@
 </script>
 
 <div class="flex flex-col gap-4 sm:gap-6 {className}">
-  {#each messageList as message (message.id)}
+  {#each messageList as message, i (message.id)}
     <div
       class="group flex {message.role === 'user'
         ? 'justify-end'
@@ -294,9 +318,11 @@
           <!-- Delete confirmation -->
           <div class="bg-red-500/10 border border-red-500/30 rounded-lg p-3">
             <p class="text-xs text-red-400 mb-3">
-              Delete this message{message.role === "user"
-                ? " and all responses after it"
-                : ""}?
+              {#if i === messageList.length - 1}
+                Delete this message?
+              {:else}
+                Delete this message and all messages after it?
+              {/if}
             </p>
             <div class="flex gap-2 justify-end">
               <button
@@ -370,10 +396,15 @@
                         class="flex items-center gap-2 bg-exo-dark-gray/60 border border-exo-yellow/20 rounded px-2 py-1 text-xs font-mono"
                       >
                         {#if attachment.type === "image" && attachment.preview}
+                          <!-- svelte-ignore a11y_no_noninteractive_element_interactions, a11y_click_events_have_key_events -->
                           <img
                             src={attachment.preview}
                             alt={attachment.name}
-                            class="w-12 h-12 object-cover rounded border border-exo-yellow/20"
+                            class="w-12 h-12 object-cover rounded border border-exo-yellow/20 cursor-pointer hover:border-exo-yellow/50 transition-colors"
+                            onclick={() => {
+                              if (attachment.preview)
+                                expandedImageSrc = attachment.preview;
+                            }}
                           />
                         {:else}
                           <span>{getAttachmentIcon(attachment)}</span>
@@ -447,15 +478,44 @@
                   <div class="mb-3">
                     {#each message.attachments.filter((a) => a.type === "generated-image") as attachment}
                       <div class="relative group/img inline-block">
+                        <!-- svelte-ignore a11y_no_noninteractive_element_interactions, a11y_click_events_have_key_events -->
                         <img
                           src={attachment.preview}
                           alt=""
-                          class="max-w-full max-h-[512px] rounded-lg border border-exo-yellow/20 shadow-lg shadow-black/20"
+                          class="max-w-full max-h-[512px] rounded-lg border border-exo-yellow/20 shadow-lg shadow-black/20 cursor-pointer"
+                          onclick={() => {
+                            if (attachment.preview)
+                              expandedImageSrc = attachment.preview;
+                          }}
                         />
                         <!-- Button overlay -->
                         <div
                           class="absolute top-2 right-2 flex gap-1 opacity-0 group-hover/img:opacity-100 transition-opacity"
                         >
+                          <!-- Expand button -->
+                          <button
+                            type="button"
+                            class="p-2 rounded-lg bg-exo-dark-gray/80 border border-exo-yellow/30 text-exo-yellow hover:bg-exo-dark-gray hover:border-exo-yellow/50 cursor-pointer"
+                            onclick={() => {
+                              if (attachment.preview)
+                                expandedImageSrc = attachment.preview;
+                            }}
+                            title="Expand image"
+                          >
+                            <svg
+                              class="w-4 h-4"
+                              fill="none"
+                              viewBox="0 0 24 24"
+                              stroke="currentColor"
+                              stroke-width="2"
+                            >
+                              <path
+                                stroke-linecap="round"
+                                stroke-linejoin="round"
+                                d="M4 8V4m0 0h4M4 4l5 5m11-1V4m0 0h-4m4 0l-5 5M4 16v4m0 0h4m-4 0l5-5m11 5l-5-5m5 5v-4m0 4h-4"
+                              />
+                            </svg>
+                          </button>
                           <!-- Edit button -->
                           <button
                             type="button"
@@ -548,13 +608,23 @@
                       >
                     </div>
                   {:else if message.content || (loading && !message.attachments?.some((a) => a.type === "generated-image"))}
-                    <MarkdownContent
-                      content={message.content || (loading ? response : "")}
-                    />
-                    {#if loading && !message.content}
-                      <span
-                        class="inline-block w-2 h-4 bg-exo-yellow/70 ml-1 cursor-blink"
-                      ></span>
+                    {#if isHeatmapVisible(message.id) && message.tokens && message.tokens.length > 0}
+                      <TokenHeatmap
+                        tokens={message.tokens}
+                        isGenerating={loading &&
+                          isLastAssistantMessage(message.id)}
+                        onRegenerateFrom={(tokenIndex) =>
+                          regenerateFromToken(message.id, tokenIndex)}
+                      />
+                    {:else}
+                      <MarkdownContent
+                        content={message.content || (loading ? response : "")}
+                      />
+                      {#if loading && !message.content}
+                        <span
+                          class="inline-block w-2 h-4 bg-exo-yellow/70 ml-1 cursor-blink"
+                        ></span>
+                      {/if}
                     {/if}
                   {/if}
                 </div>
@@ -629,6 +699,35 @@
               </button>
             {/if}
 
+            <!-- Uncertainty heatmap toggle (assistant messages with tokens) -->
+            {#if message.role === "assistant" && message.tokens && message.tokens.length > 0}
+              <button
+                onclick={() => toggleHeatmap(message.id)}
+                class="p-1.5 transition-colors rounded cursor-pointer {isHeatmapVisible(
+                  message.id,
+                )
+                  ? 'text-exo-yellow'
+                  : 'text-exo-light-gray hover:text-exo-yellow'}"
+                title={isHeatmapVisible(message.id)
+                  ? "Hide uncertainty heatmap"
+                  : "Show uncertainty heatmap"}
+              >
+                <svg
+                  class="w-3.5 h-3.5"
+                  fill="none"
+                  viewBox="0 0 24 24"
+                  stroke="currentColor"
+                >
+                  <path
+                    stroke-linecap="round"
+                    stroke-linejoin="round"
+                    stroke-width="2"
+                    d="M9 19v-6a2 2 0 00-2-2H5a2 2 0 00-2 2v6a2 2 0 002 2h2a2 2 0 002-2zm0 0V9a2 2 0 012-2h2a2 2 0 012 2v10m-6 0a2 2 0 002 2h2a2 2 0 002-2m0 0V5a2 2 0 012-2h2a2 2 0 012 2v14a2 2 0 01-2 2h-2a2 2 0 01-2-2z"
+                  />
+                </svg>
+              </button>
+            {/if}
+
             <!-- Regenerate button (last assistant message only) -->
             {#if message.role === "assistant" && isLastAssistantMessage(message.id) && !loading}
               <button
@@ -655,8 +754,13 @@
             <!-- Delete button -->
             <button
               onclick={() => handleDeleteClick(message.id)}
-              class="p-1.5 text-exo-light-gray hover:text-red-400 transition-colors rounded hover:bg-red-500/10 cursor-pointer"
-              title="Delete message"
+              disabled={loading}
+              class="p-1.5 transition-colors rounded {loading
+                ? 'text-exo-light-gray/30 cursor-not-allowed'
+                : 'text-exo-light-gray hover:text-red-400 hover:bg-red-500/10 cursor-pointer'}"
+              title={loading
+                ? "Cannot delete while generating"
+                : "Delete message"}
             >
               <svg
                 class="w-3.5 h-3.5"
@@ -731,3 +835,8 @@
     </button>
   {/if}
 </div>
+
+<ImageLightbox
+  src={expandedImageSrc}
+  onclose={() => (expandedImageSrc = null)}
+/>

dashboard/src/lib/components/FamilyLogos.svelte

@@ -0,0 +1,91 @@
+<script lang="ts">
+  type FamilyLogoProps = {
+    family: string;
+    class?: string;
+  };
+
+  let { family, class: className = "" }: FamilyLogoProps = $props();
+</script>
+
+{#if family === "favorites"}
+  <svg class="w-6 h-6 {className}" viewBox="0 0 24 24" fill="currentColor">
+    <path
+      d="M12 2l3.09 6.26L22 9.27l-5 4.87 1.18 6.88L12 17.77l-6.18 3.25L7 14.14 2 9.27l6.91-1.01L12 2z"
+    />
+  </svg>
+{:else if family === "recents"}
+  <svg class="w-6 h-6 {className}" viewBox="0 0 24 24" fill="currentColor">
+    <path
+      d="M13 3a9 9 0 0 0-9 9H1l3.89 3.89.07.14L9 12H6c0-3.87 3.13-7 7-7s7 3.13 7 7-3.13 7-7 7c-1.93 0-3.68-.79-4.94-2.06l-1.42 1.42A8.954 8.954 0 0 0 13 21a9 9 0 0 0 0-18zm-1 5v5l4.28 2.54.72-1.21-3.5-2.08V8H12z"
+    />
+  </svg>
+{:else if family === "llama" || family === "meta"}
+  <svg class="w-6 h-6 {className}" viewBox="0 0 24 24" fill="currentColor">
+    <path
+      d="M6.915 4.03c-1.968 0-3.683 1.28-4.871 3.113C.704 9.208 0 11.883 0 14.449c0 .706.07 1.369.21 1.973a6.624 6.624 0 0 0 .265.86 5.297 5.297 0 0 0 .371.761c.696 1.159 1.818 1.927 3.593 1.927 1.497 0 2.633-.671 3.965-2.444.76-1.012 1.144-1.626 2.663-4.32l.756-1.339.186-.325c.061.1.121.196.183.3l2.152 3.595c.724 1.21 1.665 2.556 2.47 3.314 1.046.987 1.992 1.22 3.06 1.22 1.075 0 1.876-.355 2.455-.843a3.743 3.743 0 0 0 .81-.973c.542-.939.861-2.127.861-3.745 0-2.72-.681-5.357-2.084-7.45-1.282-1.912-2.957-2.93-4.716-2.93-1.047 0-2.088.467-3.053 1.308-.652.57-1.257 1.29-1.82 2.05-.69-.875-1.335-1.547-1.958-2.056-1.182-.966-2.315-1.303-3.454-1.303zm10.16 2.053c1.147 0 2.188.758 2.992 1.999 1.132 1.748 1.647 4.195 1.647 6.4 0 1.548-.368 2.9-1.839 2.9-.58 0-1.027-.23-1.664-1.004-.496-.601-1.343-1.878-2.832-4.358l-.617-1.028a44.908 44.908 0 0 0-1.255-1.98c.07-.109.141-.224.211-.327 1.12-1.667 2.118-2.602 3.358-2.602zm-10.201.553c1.265 0 2.058.791 2.675 1.446.307.327.737.871 1.234 1.579l-1.02 1.566c-.757 1.163-1.882 3.017-2.837 4.338-1.191 1.649-1.81 1.817-2.486 1.817-.524 0-1.038-.237-1.383-.794-.263-.426-.464-1.13-.464-2.046 0-2.221.63-4.535 1.66-6.088.454-.687.964-1.226 1.533-1.533a2.264 2.264 0 0 1 1.088-.285z"
+    />
+  </svg>
+{:else if family === "qwen"}
+  <svg class="w-6 h-6 {className}" viewBox="0 0 24 24" fill="currentColor">
+    <path
+      d="M12.604 1.34c.393.69.784 1.382 1.174 2.075a.18.18 0 00.157.091h5.552c.174 0 .322.11.446.327l1.454 2.57c.19.337.24.478.024.837-.26.43-.513.864-.76 1.3l-.367.658c-.106.196-.223.28-.04.512l2.652 4.637c.172.301.111.494-.043.77-.437.785-.882 1.564-1.335 2.34-.159.272-.352.375-.68.37-.777-.016-1.552-.01-2.327.016a.099.099 0 00-.081.05 575.097 575.097 0 01-2.705 4.74c-.169.293-.38.363-.725.364-.997.003-2.002.004-3.017.002a.537.537 0 01-.465-.271l-1.335-2.323a.09.09 0 00-.083-.049H4.982c-.285.03-.553-.001-.805-.092l-1.603-2.77a.543.543 0 01-.002-.54l1.207-2.12a.198.198 0 000-.197 550.951 550.951 0 01-1.875-3.272l-.79-1.395c-.16-.31-.173-.496.095-.965.465-.813.927-1.625 1.387-2.436.132-.234.304-.334.584-.335a338.3 338.3 0 012.589-.001.124.124 0 00.107-.063l2.806-4.895a.488.488 0 01.422-.246c.524-.001 1.053 0 1.583-.006L11.704 1c.341-.003.724.032.9.34zm-3.432.403a.06.06 0 00-.052.03L6.254 6.788a.157.157 0 01-.135.078H3.253c-.056 0-.07.025-.041.074l5.81 10.156c.025.042.013.062-.034.063l-2.795.015a.218.218 0 00-.2.116l-1.32 2.31c-.044.078-.021.118.068.118l5.716.008c.046 0 .08.02.104.061l1.403 2.454c.046.081.092.082.139 0l5.006-8.76.783-1.382a.055.055 0 01.096 0l1.424 2.53a.122.122 0 00.107.062l2.763-.02a.04.04 0 00.035-.02.041.041 0 000-.04l-2.9-5.086a.108.108 0 010-.113l.293-.507 1.12-1.977c.024-.041.012-.062-.035-.062H9.2c-.059 0-.073-.026-.043-.077l1.434-2.505a.107.107 0 000-.114L9.225 1.774a.06.06 0 00-.053-.031zm6.29 8.02c.046 0 .058.02.034.06l-.832 1.465-2.613 4.585a.056.056 0 01-.05.029.058.058 0 01-.05-.029L8.498 9.841c-.02-.034-.01-.052.028-.054l.216-.012 6.722-.012z"
+    />
+  </svg>
+{:else if family === "deepseek"}
+  <svg class="w-6 h-6 {className}" viewBox="0 0 24 24" fill="currentColor">
+    <path
+      d="M23.748 4.482c-.254-.124-.364.113-.512.234-.051.039-.094.09-.137.136-.372.397-.806.657-1.373.626-.829-.046-1.537.214-2.163.848-.133-.782-.575-1.248-1.247-1.548-.352-.156-.708-.311-.955-.65-.172-.241-.219-.51-.305-.774-.055-.16-.11-.323-.293-.35-.2-.031-.278.136-.356.276-.313.572-.434 1.202-.422 1.84.027 1.436.633 2.58 1.838 3.393.137.093.172.187.129.323-.082.28-.18.552-.266.833-.055.179-.137.217-.329.14a5.526 5.526 0 01-1.736-1.18c-.857-.828-1.631-1.742-2.597-2.458a11.365 11.365 0 00-.689-.471c-.985-.957.13-1.743.388-1.836.27-.098.093-.432-.779-.428-.872.004-1.67.295-2.687.684a3.055 3.055 0 01-.465.137 9.597 9.597 0 00-2.883-.102c-1.885.21-3.39 1.102-4.497 2.623C.082 8.606-.231 10.684.152 12.85c.403 2.284 1.569 4.175 3.36 5.653 1.858 1.533 3.997 2.284 6.438 2.14 1.482-.085 3.133-.284 4.994-1.86.47.234.962.327 1.78.397.63.059 1.236-.03 1.705-.128.735-.156.684-.837.419-.961-2.155-1.004-1.682-.595-2.113-.926 1.096-1.296 2.746-2.642 3.392-7.003.05-.347.007-.565 0-.845-.004-.17.035-.237.23-.256a4.173 4.173 0 001.545-.475c1.396-.763 1.96-2.015 2.093-3.517.02-.23-.004-.467-.247-.588zM11.581 18c-2.089-1.642-3.102-2.183-3.52-2.16-.392.024-.321.471-.235.763.09.288.207.486.371.739.114.167.192.416-.113.603-.673.416-1.842-.14-1.897-.167-1.361-.802-2.5-1.86-3.301-3.307-.774-1.393-1.224-2.887-1.298-4.482-.02-.386.093-.522.477-.592a4.696 4.696 0 011.529-.039c2.132.312 3.946 1.265 5.468 2.774.868.86 1.525 1.887 2.202 2.891.72 1.066 1.494 2.082 2.48 2.914.348.292.625.514.891.677-.802.09-2.14.11-3.054-.614zm1-6.44a.306.306 0 01.415-.287.302.302 0 01.2.288.306.306 0 01-.31.307.303.303 0 01-.304-.308zm3.11 1.596c-.2.081-.399.151-.59.16a1.245 1.245 0 01-.798-.254c-.274-.23-.47-.358-.552-.758a1.73 1.73 0 01.016-.588c.07-.327-.008-.537-.239-.727-.187-.156-.426-.199-.688-.199a.559.559 0 01-.254-.078c-.11-.054-.2-.19-.114-.358.028-.054.16-.186.192-.21.356-.202.767-.136 1.146.016.352.144.618.408 1.001.782.391.451.462.576.685.914.176.265.336.537.445.848.067.195-.019.354-.25.452z"
+    />
+  </svg>
+{:else if family === "openai" || family === "gpt-oss"}
+  <svg class="w-6 h-6 {className}" viewBox="0 0 24 24" fill="currentColor">
+    <path
+      d="M22.2819 9.8211a5.9847 5.9847 0 0 0-.5157-4.9108 6.0462 6.0462 0 0 0-6.5098-2.9A6.0651 6.0651 0 0 0 4.9807 4.1818a5.9847 5.9847 0 0 0-3.9977 2.9 6.0462 6.0462 0 0 0 .7427 7.0966 5.98 5.98 0 0 0 .511 4.9107 6.051 6.051 0 0 0 6.5146 2.9001A5.9847 5.9847 0 0 0 13.2599 24a6.0557 6.0557 0 0 0 5.7718-4.2058 5.9894 5.9894 0 0 0 3.9977-2.9001 6.0557 6.0557 0 0 0-.7475-7.0729zm-9.022 12.6081a4.4755 4.4755 0 0 1-2.8764-1.0408l.1419-.0804 4.7783-2.7582a.7948.7948 0 0 0 .3927-.6813v-6.7369l2.02 1.1686a.071.071 0 0 1 .038.052v5.5826a4.504 4.504 0 0 1-4.4945 4.4944zm-9.6607-4.1254a4.4708 4.4708 0 0 1-.5346-3.0137l.142.0852 4.783 2.7582a.7712.7712 0 0 0 .7806 0l5.8428-3.3685v2.3324a.0804.0804 0 0 1-.0332.0615L9.74 19.9502a4.4992 4.4992 0 0 1-6.1408-1.6464zM2.3408 7.8956a4.485 4.485 0 0 1 2.3655-1.9728V11.6a.7664.7664 0 0 0 .3879.6765l5.8144 3.3543-2.0201 1.1685a.0757.0757 0 0 1-.071 0l-4.8303-2.7865A4.504 4.504 0 0 1 2.3408 7.872zm16.5963 3.8558L13.1038 8.364 15.1192 7.2a.0757.0757 0 0 1 .071 0l4.8303 2.7913a4.4944 4.4944 0 0 1-.6765 8.1042v-5.6772a.79.79 0 0 0-.407-.667zm2.0107-3.0231l-.142-.0852-4.7735-2.7818a.7759.7759 0 0 0-.7854 0L9.409 9.2297V6.8974a.0662.0662 0 0 1 .0284-.0615l4.8303-2.7866a4.4992 4.4992 0 0 1 6.6802 4.66zM8.3065 12.863l-2.02-1.1638a.0804.0804 0 0 1-.038-.0567V6.0742a4.4992 4.4992 0 0 1 7.3757-3.4537l-.142.0805L8.704 5.459a.7948.7948 0 0 0-.3927.6813zm1.0976-2.3654l2.602-1.4998 2.6069 1.4998v2.9994l-2.5974 1.4997-2.6067-1.4997Z"
+    />
+  </svg>
+{:else if family === "glm"}
+  <svg class="w-6 h-6 {className}" viewBox="0 0 24 24" fill="currentColor">
+    <path
+      d="M11.991 23.503a.24.24 0 00-.244.248.24.24 0 00.244.249.24.24 0 00.245-.249.24.24 0 00-.22-.247l-.025-.001zM9.671 5.365a1.697 1.697 0 011.099 2.132l-.071.172-.016.04-.018.054c-.07.16-.104.32-.104.498-.035.71.47 1.279 1.186 1.314h.366c1.309.053 2.338 1.173 2.286 2.523-.052 1.332-1.152 2.38-2.478 2.327h-.174c-.715.018-1.274.64-1.239 1.368 0 .124.018.23.053.337.209.373.54.658.96.8.75.23 1.517-.125 1.9-.782l.018-.035c.402-.64 1.17-.96 1.92-.711.854.284 1.378 1.226 1.099 2.167a1.661 1.661 0 01-2.077 1.102 1.711 1.711 0 01-.907-.711l-.017-.035c-.2-.323-.463-.58-.851-.711l-.056-.018a1.646 1.646 0 00-1.954.746 1.66 1.66 0 01-1.065.764 1.677 1.677 0 01-1.989-1.279c-.209-.906.332-1.83 1.257-2.043a1.51 1.51 0 01.296-.035h.018c.68-.071 1.151-.622 1.116-1.333a1.307 1.307 0 00-.227-.693 2.515 2.515 0 01-.366-1.403 2.39 2.39 0 01.366-1.208c.14-.195.21-.444.227-.693.018-.71-.506-1.261-1.186-1.332l-.07-.018a1.43 1.43 0 01-.299-.07l-.05-.019a1.7 1.7 0 01-1.047-2.114 1.68 1.68 0 012.094-1.101zm-5.575 10.11c.26-.264.639-.367.994-.27.355.096.633.379.728.74.095.362-.007.748-.267 1.013-.402.41-1.053.41-1.455 0a1.062 1.062 0 010-1.482zm14.845-.294c.359-.09.738.024.992.297.254.274.344.665.237 1.025-.107.36-.396.634-.756.718-.551.128-1.1-.22-1.23-.781a1.05 1.05 0 01.757-1.26zm-.064-4.39c.314.32.49.753.49 1.206 0 .452-.176.886-.49 1.206-.315.32-.74.5-1.185.5-.444 0-.87-.18-1.184-.5a1.727 1.727 0 010-2.412 1.654 1.654 0 012.369 0zm-11.243.163c.364.484.447 1.128.218 1.691a1.665 1.665 0 01-2.188.923c-.855-.36-1.26-1.358-.907-2.228a1.68 1.68 0 011.33-1.038c.593-.08 1.183.169 1.547.652zm11.545-4.221c.368 0 .708.2.892.524.184.324.184.724 0 1.048a1.026 1.026 0 01-.892.524c-.568 0-1.03-.47-1.03-1.048 0-.579.462-1.048 1.03-1.048zm-14.358 0c.368 0 .707.2.891.524.184.324.184.724 0 1.048a1.026 1.026 0 01-.891.524c-.569 0-1.03-.47-1.03-1.048 0-.579.461-1.048 1.03-1.048zm10.031-1.475c.925 0 1.675.764 1.675 1.706s-.75 1.705-1.675 1.705-1.674-.763-1.674-1.705c0-.942.75-1.706 1.674-1.706zm-2.626-.684c.362-.082.653-.356.761-.718a1.062 1.062 0 00-.238-1.028 1.017 1.017 0 00-.996-.294c-.547.14-.881.7-.752 1.257.13.558.675.907 1.225.783zm0 16.876c.359-.087.644-.36.75-.72a1.062 1.062 0 00-.237-1.019 1.018 1.018 0 00-.985-.301 1.037 1.037 0 00-.762.717c-.108.361-.017.754.239 1.028.245.263.606.377.953.305l.043-.01zM17.19 3.5a.631.631 0 00.628-.64c0-.355-.279-.64-.628-.64a.631.631 0 00-.628.64c0 .355.28.64.628.64zm-10.38 0a.631.631 0 00.628-.64c0-.355-.28-.64-.628-.64a.631.631 0 00-.628.64c0 .355.279.64.628.64zm-5.182 7.852a.631.631 0 00-.628.64c0 .354.28.639.628.639a.63.63 0 00.627-.606l.001-.034a.62.62 0 00-.628-.64zm5.182 9.13a.631.631 0 00-.628.64c0 .355.279.64.628.64a.631.631 0 00.628-.64c0-.355-.28-.64-.628-.64zm10.38.018a.631.631 0 00-.628.64c0 .355.28.64.628.64a.631.631 0 00.628-.64c0-.355-.279-.64-.628-.64zm5.182-9.148a.631.631 0 00-.628.64c0 .354.279.639.628.639a.631.631 0 00.628-.64c0-.355-.28-.64-.628-.64zm-.384-4.992a.24.24 0 00.244-.249.24.24 0 00-.244-.249.24.24 0 00-.244.249c0 .142.122.249.244.249zM11.991.497a.24.24 0 00.245-.248A.24.24 0 0011.99 0a.24.24 0 00-.244.249c0 .133.108.236.223.247l.021.001zM2.011 6.36a.24.24 0 00.245-.249.24.24 0 00-.244-.249.24.24 0 00-.244.249.24.24 0 00.244.249zm0 11.263a.24.24 0 00-.243.248.24.24 0 00.244.249.24.24 0 00.244-.249.252.252 0 00-.244-.248zm19.995-.018a.24.24 0 00-.245.248.24.24 0 00.245.25.24.24 0 00.244-.25.252.252 0 00-.244-.248z"
+    />
+  </svg>
+{:else if family === "minimax"}
+  <svg class="w-6 h-6 {className}" viewBox="0 0 24 24" fill="currentColor">
+    <path
+      d="M16.278 2c1.156 0 2.093.927 2.093 2.07v12.501a.74.74 0 00.744.709.74.74 0 00.743-.709V9.099a2.06 2.06 0 012.071-2.049A2.06 2.06 0 0124 9.1v6.561a.649.649 0 01-.652.645.649.649 0 01-.653-.645V9.1a.762.762 0 00-.766-.758.762.762 0 00-.766.758v7.472a2.037 2.037 0 01-2.048 2.026 2.037 2.037 0 01-2.048-2.026v-12.5a.785.785 0 00-.788-.753.785.785 0 00-.789.752l-.001 15.904A2.037 2.037 0 0113.441 22a2.037 2.037 0 01-2.048-2.026V18.04c0-.356.292-.645.652-.645.36 0 .652.289.652.645v1.934c0 .263.142.506.372.638.23.131.514.131.744 0a.734.734 0 00.372-.638V4.07c0-1.143.937-2.07 2.093-2.07zm-5.674 0c1.156 0 2.093.927 2.093 2.07v11.523a.648.648 0 01-.652.645.648.648 0 01-.652-.645V4.07a.785.785 0 00-.789-.78.785.785 0 00-.789.78v14.013a2.06 2.06 0 01-2.07 2.048 2.06 2.06 0 01-2.071-2.048V9.1a.762.762 0 00-.766-.758.762.762 0 00-.766.758v3.8a2.06 2.06 0 01-2.071 2.049A2.06 2.06 0 010 12.9v-1.378c0-.357.292-.646.652-.646.36 0 .653.29.653.646V12.9c0 .418.343.757.766.757s.766-.339.766-.757V9.099a2.06 2.06 0 012.07-2.048 2.06 2.06 0 012.071 2.048v8.984c0 .419.343.758.767.758.423 0 .766-.339.766-.758V4.07c0-1.143.937-2.07 2.093-2.07z"
+    />
+  </svg>
+{:else if family === "kimi"}
+  <svg class="w-6 h-6 {className}" viewBox="0 0 24 24" fill="currentColor">
+    <path
+      d="M19.738 5.776c.163-.209.306-.4.457-.585.07-.087.064-.153-.004-.244-.655-.861-.717-1.817-.34-2.787.283-.73.909-1.072 1.674-1.145.477-.045.945.004 1.379.236.57.305.902.77 1.01 1.412.086.512.07 1.012-.075 1.508-.257.878-.888 1.333-1.753 1.448-.718.096-1.446.108-2.17.157-.056.004-.113 0-.178 0z"
+    />
+    <path
+      d="M17.962 1.844h-4.326l-3.425 7.81H5.369V1.878H1.5V22h3.87v-8.477h6.824a3.025 3.025 0 002.743-1.75V22h3.87v-8.477a3.87 3.87 0 00-3.588-3.86v-.01h-2.125a3.94 3.94 0 002.323-2.12l2.545-5.689z"
+    />
+  </svg>
+{:else if family === "flux"}
+  <svg class="w-6 h-6 {className}" viewBox="0 0 24 24" fill="currentColor">
+    <path
+      d="M12 2L2 19h7.5l2.5-4.5L14.5 19H22L12 2zm0 4.5L16.5 17h-3l-1.5-2.7L10.5 17h-3L12 6.5z"
+    />
+  </svg>
+{:else if family === "qwen-image"}
+  <svg class="w-6 h-6 {className}" viewBox="0 0 24 24" fill="currentColor">
+    <path
+      d="M12.604 1.34c.393.69.784 1.382 1.174 2.075a.18.18 0 00.157.091h5.552c.174 0 .322.11.446.327l1.454 2.57c.19.337.24.478.024.837-.26.43-.513.864-.76 1.3l-.367.658c-.106.196-.223.28-.04.512l2.652 4.637c.172.301.111.494-.043.77-.437.785-.882 1.564-1.335 2.34-.159.272-.352.375-.68.37-.777-.016-1.552-.01-2.327.016a.099.099 0 00-.081.05 575.097 575.097 0 01-2.705 4.74c-.169.293-.38.363-.725.364-.997.003-2.002.004-3.017.002a.537.537 0 01-.465-.271l-1.335-2.323a.09.09 0 00-.083-.049H4.982c-.285.03-.553-.001-.805-.092l-1.603-2.77a.543.543 0 01-.002-.54l1.207-2.12a.198.198 0 000-.197 550.951 550.951 0 01-1.875-3.272l-.79-1.395c-.16-.31-.173-.496.095-.965.465-.813.927-1.625 1.387-2.436.132-.234.304-.334.584-.335a338.3 338.3 0 012.589-.001.124.124 0 00.107-.063l2.806-4.895a.488.488 0 01.422-.246c.524-.001 1.053 0 1.583-.006L11.704 1c.341-.003.724.032.9.34zm-3.432.403a.06.06 0 00-.052.03L6.254 6.788a.157.157 0 01-.135.078H3.253c-.056 0-.07.025-.041.074l5.81 10.156c.025.042.013.062-.034.063l-2.795.015a.218.218 0 00-.2.116l-1.32 2.31c-.044.078-.021.118.068.118l5.716.008c.046 0 .08.02.104.061l1.403 2.454c.046.081.092.082.139 0l5.006-8.76.783-1.382a.055.055 0 01.096 0l1.424 2.53a.122.122 0 00.107.062l2.763-.02a.04.04 0 00.035-.02.041.041 0 000-.04l-2.9-5.086a.108.108 0 010-.113l.293-.507 1.12-1.977c.024-.041.012-.062-.035-.062H9.2c-.059 0-.073-.026-.043-.077l1.434-2.505a.107.107 0 000-.114L9.225 1.774a.06.06 0 00-.053-.031zm6.29 8.02c.046 0 .058.02.034.06l-.832 1.465-2.613 4.585a.056.056 0 01-.05.029.058.058 0 01-.05-.029L8.498 9.841c-.02-.034-.01-.052.028-.054l.216-.012 6.722-.012z"
+    />
+  </svg>
+{:else if family === "huggingface"}
+  <svg class="w-6 h-6 {className}" viewBox="0 0 24 24" fill="currentColor">
+    <path
+      d="M12.025 1.13c-5.77 0-10.449 4.647-10.449 10.378 0 1.112.178 2.181.503 3.185.064-.222.203-.444.416-.577a.96.96 0 0 1 .524-.15c.293 0 .584.124.84.284.278.173.48.408.71.694.226.282.458.611.684.951v-.014c.017-.324.106-.622.264-.874s.403-.487.762-.543c.3-.047.596.06.787.203s.31.313.4.467c.15.257.212.468.233.542.01.026.653 1.552 1.657 2.54.616.605 1.01 1.223 1.082 1.912.055.537-.096 1.059-.38 1.572.637.121 1.294.187 1.967.187.657 0 1.298-.063 1.921-.178-.287-.517-.44-1.041-.384-1.581.07-.69.465-1.307 1.081-1.913 1.004-.987 1.647-2.513 1.657-2.539.021-.074.083-.285.233-.542.09-.154.208-.323.4-.467a1.08 1.08 0 0 1 .787-.203c.359.056.604.29.762.543s.247.55.265.874v.015c.225-.34.457-.67.683-.952.23-.286.432-.52.71-.694.257-.16.547-.284.84-.285a.97.97 0 0 1 .524.151c.228.143.373.388.43.625l.006.04a10.3 10.3 0 0 0 .534-3.273c0-5.731-4.678-10.378-10.449-10.378M8.327 6.583a1.5 1.5 0 0 1 .713.174 1.487 1.487 0 0 1 .617 2.013c-.183.343-.762-.214-1.102-.094-.38.134-.532.914-.917.71a1.487 1.487 0 0 1 .69-2.803m7.486 0a1.487 1.487 0 0 1 .689 2.803c-.385.204-.536-.576-.916-.71-.34-.12-.92.437-1.103.094a1.487 1.487 0 0 1 .617-2.013 1.5 1.5 0 0 1 .713-.174m-10.68 1.55a.96.96 0 1 1 0 1.921.96.96 0 0 1 0-1.92m13.838 0a.96.96 0 1 1 0 1.92.96.96 0 0 1 0-1.92M8.489 11.458c.588.01 1.965 1.157 3.572 1.164 1.607-.007 2.984-1.155 3.572-1.164.196-.003.305.12.305.454 0 .886-.424 2.328-1.563 3.202-.22-.756-1.396-1.366-1.63-1.32q-.011.001-.02.006l-.044.026-.01.008-.03.024q-.018.017-.035.036l-.032.04a1 1 0 0 0-.058.09l-.014.025q-.049.088-.11.19a1 1 0 0 1-.083.116 1.2 1.2 0 0 1-.173.18q-.035.029-.075.058a1.3 1.3 0 0 1-.251-.243 1 1 0 0 1-.076-.107c-.124-.193-.177-.363-.337-.444-.034-.016-.104-.008-.2.022q-.094.03-.216.087-.06.028-.125.063l-.13.074q-.067.04-.136.086a3 3 0 0 0-.135.096 3 3 0 0 0-.26.219 2 2 0 0 0-.12.121 2 2 0 0 0-.106.128l-.002.002a2 2 0 0 0-.09.132l-.001.001a1.2 1.2 0 0 0-.105.212q-.013.036-.024.073c-1.139-.875-1.563-2.317-1.563-3.203 0-.334.109-.457.305-.454m.836 10.354c.824-1.19.766-2.082-.365-3.194-1.13-1.112-1.789-2.738-1.789-2.738s-.246-.945-.806-.858-.97 1.499.202 2.362c1.173.864-.233 1.45-.685.64-.45-.812-1.683-2.896-2.322-3.295s-1.089-.175-.938.647 2.822 2.813 2.562 3.244-1.176-.506-1.176-.506-2.866-2.567-3.49-1.898.473 1.23 2.037 2.16c1.564.932 1.686 1.178 1.464 1.53s-3.675-2.511-4-1.297c-.323 1.214 3.524 1.567 3.287 2.405-.238.839-2.71-1.587-3.216-.642-.506.946 3.49 2.056 3.522 2.064 1.29.33 4.568 1.028 5.713-.624m5.349 0c-.824-1.19-.766-2.082.365-3.194 1.13-1.112 1.789-2.738 1.789-2.738s.246-.945.806-.858.97 1.499-.202 2.362c-1.173.864.233 1.45.685.64.451-.812 1.683-2.896 2.322-3.295s1.089-.175.938.647-2.822 2.813-2.562 3.244 1.176-.506 1.176-.506 2.866-2.567 3.49-1.898-.473 1.23-2.037 2.16c-1.564.932-1.686 1.178-1.464 1.53s3.675-2.511 4-1.297c.323 1.214-3.524 1.567-3.287 2.405.238.839 2.71-1.587 3.216-.642.506.946-3.49 2.056-3.522 2.064-1.29.33-4.568 1.028-5.713-.624"
+    />
+  </svg>
+{:else}
+  <svg class="w-6 h-6 {className}" viewBox="0 0 24 24" fill="currentColor">
+    <path
+      d="M12 2C6.48 2 2 6.48 2 12s4.48 10 10 10 10-4.48 10-10S17.52 2 12 2zm-2 15l-5-5 1.41-1.41L10 14.17l7.59-7.59L19 8l-9 9z"
+    />
+  </svg>
+{/if}

dashboard/src/lib/components/FamilySidebar.svelte

@@ -0,0 +1,176 @@
+<script lang="ts">
+  import FamilyLogos from "./FamilyLogos.svelte";
+
+  type FamilySidebarProps = {
+    families: string[];
+    selectedFamily: string | null;
+    hasFavorites: boolean;
+    hasRecents: boolean;
+    onSelect: (family: string | null) => void;
+  };
+
+  let {
+    families,
+    selectedFamily,
+    hasFavorites,
+    hasRecents,
+    onSelect,
+  }: FamilySidebarProps = $props();
+
+  // Family display names
+  const familyNames: Record<string, string> = {
+    favorites: "Favorites",
+    recents: "Recent",
+    huggingface: "Hub",
+    llama: "Meta",
+    qwen: "Qwen",
+    deepseek: "DeepSeek",
+    "gpt-oss": "OpenAI",
+    glm: "GLM",
+    minimax: "MiniMax",
+    kimi: "Kimi",
+    flux: "FLUX",
+    "qwen-image": "Qwen Img",
+  };
+
+  function getFamilyName(family: string): string {
+    return (
+      familyNames[family] || family.charAt(0).toUpperCase() + family.slice(1)
+    );
+  }
+</script>
+
+<div
+  class="flex flex-col gap-1 py-2 px-1 border-r border-exo-yellow/10 bg-exo-medium-gray/30 min-w-[64px] overflow-y-auto scrollbar-hide"
+>
+  <!-- All models (no filter) -->
+  <button
+    type="button"
+    onclick={() => onSelect(null)}
+    class="group flex flex-col items-center justify-center p-2 rounded transition-all duration-200 cursor-pointer {selectedFamily ===
+    null
+      ? 'bg-exo-yellow/20 border-l-2 border-exo-yellow'
+      : 'hover:bg-white/5 border-l-2 border-transparent'}"
+    title="All models"
+  >
+    <svg
+      class="w-5 h-5 {selectedFamily === null
+        ? 'text-exo-yellow'
+        : 'text-white/50 group-hover:text-white/70'}"
+      viewBox="0 0 24 24"
+      fill="currentColor"
+    >
+      <path
+        d="M4 8h4V4H4v4zm6 12h4v-4h-4v4zm-6 0h4v-4H4v4zm0-6h4v-4H4v4zm6 0h4v-4h-4v4zm6-10v4h4V4h-4zm-6 4h4V4h-4v4zm6 6h4v-4h-4v4zm0 6h4v-4h-4v4z"
+      />
+    </svg>
+    <span
+      class="text-[9px] font-mono mt-0.5 {selectedFamily === null
+        ? 'text-exo-yellow'
+        : 'text-white/40 group-hover:text-white/60'}">All</span
+    >
+  </button>
+
+  <!-- Favorites (only show if has favorites) -->
+  {#if hasFavorites}
+    <button
+      type="button"
+      onclick={() => onSelect("favorites")}
+      class="group flex flex-col items-center justify-center p-2 rounded transition-all duration-200 cursor-pointer {selectedFamily ===
+      'favorites'
+        ? 'bg-exo-yellow/20 border-l-2 border-exo-yellow'
+        : 'hover:bg-white/5 border-l-2 border-transparent'}"
+      title="Show favorited models"
+    >
+      <FamilyLogos
+        family="favorites"
+        class={selectedFamily === "favorites"
+          ? "text-amber-400"
+          : "text-white/50 group-hover:text-amber-400/70"}
+      />
+      <span
+        class="text-[9px] font-mono mt-0.5 {selectedFamily === 'favorites'
+          ? 'text-amber-400'
+          : 'text-white/40 group-hover:text-white/60'}">Faves</span
+      >
+    </button>
+  {/if}
+
+  <!-- Recent (only show if has recent models) -->
+  {#if hasRecents}
+    <button
+      type="button"
+      onclick={() => onSelect("recents")}
+      class="group flex flex-col items-center justify-center p-2 rounded transition-all duration-200 cursor-pointer {selectedFamily ===
+      'recents'
+        ? 'bg-exo-yellow/20 border-l-2 border-exo-yellow'
+        : 'hover:bg-white/5 border-l-2 border-transparent'}"
+      title="Recently launched models"
+    >
+      <FamilyLogos
+        family="recents"
+        class={selectedFamily === "recents"
+          ? "text-exo-yellow"
+          : "text-white/50 group-hover:text-white/70"}
+      />
+      <span
+        class="text-[9px] font-mono mt-0.5 {selectedFamily === 'recents'
+          ? 'text-exo-yellow'
+          : 'text-white/40 group-hover:text-white/60'}">Recent</span
+      >
+    </button>
+  {/if}
+
+  <!-- HuggingFace Hub -->
+  <button
+    type="button"
+    onclick={() => onSelect("huggingface")}
+    class="group flex flex-col items-center justify-center p-2 rounded transition-all duration-200 cursor-pointer {selectedFamily ===
+    'huggingface'
+      ? 'bg-orange-500/20 border-l-2 border-orange-400'
+      : 'hover:bg-white/5 border-l-2 border-transparent'}"
+    title="Browse and add models from Hugging Face"
+  >
+    <FamilyLogos
+      family="huggingface"
+      class={selectedFamily === "huggingface"
+        ? "text-orange-400"
+        : "text-white/50 group-hover:text-orange-400/70"}
+    />
+    <span
+      class="text-[9px] font-mono mt-0.5 {selectedFamily === 'huggingface'
+        ? 'text-orange-400'
+        : 'text-white/40 group-hover:text-white/60'}">Hub</span
+    >
+  </button>
+
+  <div class="h-px bg-exo-yellow/10 my-1"></div>
+
+  <!-- Model families -->
+  {#each families as family}
+    <button
+      type="button"
+      onclick={() => onSelect(family)}
+      class="group flex flex-col items-center justify-center p-2 rounded transition-all duration-200 cursor-pointer {selectedFamily ===
+      family
+        ? 'bg-exo-yellow/20 border-l-2 border-exo-yellow'
+        : 'hover:bg-white/5 border-l-2 border-transparent'}"
+      title={getFamilyName(family)}
+    >
+      <FamilyLogos
+        {family}
+        class={selectedFamily === family
+          ? "text-exo-yellow"
+          : "text-white/50 group-hover:text-white/70"}
+      />
+      <span
+        class="text-[9px] font-mono mt-0.5 truncate max-w-full {selectedFamily ===
+        family
+          ? 'text-exo-yellow'
+          : 'text-white/40 group-hover:text-white/60'}"
+      >
+        {getFamilyName(family)}
+      </span>
+    </button>
+  {/each}
+</div>

dashboard/src/lib/components/HuggingFaceResultItem.svelte

@@ -0,0 +1,151 @@
+<script lang="ts">
+  interface HuggingFaceModel {
+    id: string;
+    author: string;
+    downloads: number;
+    likes: number;
+    last_modified: string;
+    tags: string[];
+  }
+
+  type HuggingFaceResultItemProps = {
+    model: HuggingFaceModel;
+    isAdded: boolean;
+    isAdding: boolean;
+    onAdd: () => void;
+    onSelect: () => void;
+    downloadedOnNodes?: string[];
+  };
+
+  let {
+    model,
+    isAdded,
+    isAdding,
+    onAdd,
+    onSelect,
+    downloadedOnNodes = [],
+  }: HuggingFaceResultItemProps = $props();
+
+  function formatNumber(num: number): string {
+    if (num >= 1000000) {
+      return `${(num / 1000000).toFixed(1)}M`;
+    } else if (num >= 1000) {
+      return `${(num / 1000).toFixed(1)}k`;
+    }
+    return num.toString();
+  }
+
+  // Extract model name from full ID (e.g., "mlx-community/Llama-3.2-1B" -> "Llama-3.2-1B")
+  const modelName = $derived(model.id.split("/").pop() || model.id);
+</script>
+
+<div
+  class="flex items-center justify-between gap-3 px-3 py-2.5 hover:bg-white/5 transition-colors border-b border-white/5 last:border-b-0"
+>
+  <div class="flex-1 min-w-0">
+    <div class="flex items-center gap-2">
+      <span class="text-sm font-mono text-white truncate" title={model.id}
+        >{modelName}</span
+      >
+      {#if downloadedOnNodes.length > 0}
+        <span
+          class="flex-shrink-0"
+          title={`Downloaded on ${downloadedOnNodes.join(", ")}`}
+        >
+          <svg
+            class="w-4 h-4"
+            viewBox="0 0 24 24"
+            fill="none"
+            stroke="currentColor"
+            stroke-width="2"
+            stroke-linecap="round"
+            stroke-linejoin="round"
+          >
+            <path
+              class="text-white/40"
+              d="M20 20a2 2 0 0 0 2-2V8a2 2 0 0 0-2-2h-7.9a2 2 0 0 1-1.69-.9L9.6 3.9A2 2 0 0 0 7.93 3H4a2 2 0 0 0-2 2v13a2 2 0 0 0 2 2Z"
+            />
+            <path class="text-green-400" d="m9 13 2 2 4-4" />
+          </svg>
+        </span>
+      {/if}
+      {#if isAdded}
+        <span
+          class="px-1.5 py-0.5 text-[10px] font-mono bg-green-500/20 text-green-400 rounded"
+          >Added</span
+        >
+      {/if}
+    </div>
+    <div class="flex items-center gap-3 mt-0.5 text-xs text-white/40">
+      <span class="truncate">{model.author}</span>
+      <span
+        class="flex items-center gap-1 shrink-0"
+        title="Downloads in the last 30 days"
+      >
+        <svg
+          class="w-3 h-3"
+          fill="none"
+          stroke="currentColor"
+          viewBox="0 0 24 24"
+        >
+          <path
+            stroke-linecap="round"
+            stroke-linejoin="round"
+            stroke-width="2"
+            d="M4 16v1a3 3 0 003 3h10a3 3 0 003-3v-1m-4-4l-4 4m0 0l-4-4m4 4V4"
+          />
+        </svg>
+        {formatNumber(model.downloads)}
+      </span>
+      <span
+        class="flex items-center gap-1 shrink-0"
+        title="Community likes on Hugging Face"
+      >
+        <svg
+          class="w-3 h-3"
+          fill="none"
+          stroke="currentColor"
+          viewBox="0 0 24 24"
+        >
+          <path
+            stroke-linecap="round"
+            stroke-linejoin="round"
+            stroke-width="2"
+            d="M4.318 6.318a4.5 4.5 0 000 6.364L12 20.364l7.682-7.682a4.5 4.5 0 00-6.364-6.364L12 7.636l-1.318-1.318a4.5 4.5 0 00-6.364 0z"
+          />
+        </svg>
+        {formatNumber(model.likes)}
+      </span>
+    </div>
+  </div>
+
+  <div class="flex items-center gap-2 shrink-0">
+    {#if isAdded}
+      <button
+        type="button"
+        onclick={onSelect}
+        class="px-3 py-1.5 text-xs font-mono tracking-wider uppercase bg-exo-yellow/10 text-exo-yellow border border-exo-yellow/30 hover:bg-exo-yellow/20 transition-colors rounded cursor-pointer"
+      >
+        Select
+      </button>
+    {:else}
+      <button
+        type="button"
+        onclick={onAdd}
+        disabled={isAdding}
+        class="px-3 py-1.5 text-xs font-mono tracking-wider uppercase bg-orange-500/10 text-orange-400 border border-orange-400/30 hover:bg-orange-500/20 transition-colors rounded cursor-pointer disabled:opacity-50 disabled:cursor-not-allowed"
+      >
+        {#if isAdding}
+          <span class="flex items-center gap-1.5">
+            <span
+              class="w-3 h-3 border-2 border-orange-400 border-t-transparent rounded-full animate-spin"
+            ></span>
+            Adding...
+          </span>
+        {:else}
+          + Add
+        {/if}
+      </button>
+    {/if}
+  </div>
+</div>

dashboard/src/lib/components/ImageLightbox.svelte

@@ -0,0 +1,96 @@
+<script lang="ts">
+  import { fade, fly } from "svelte/transition";
+  import { cubicOut } from "svelte/easing";
+
+  interface Props {
+    src: string | null;
+    onclose: () => void;
+  }
+
+  let { src, onclose }: Props = $props();
+
+  function handleKeydown(e: KeyboardEvent) {
+    if (e.key === "Escape") {
+      onclose();
+    }
+  }
+
+  function extensionFromSrc(dataSrc: string): string {
+    const match = dataSrc.match(/^data:image\/(\w+)/);
+    if (match) return match[1] === "jpeg" ? "jpg" : match[1];
+    const urlMatch = dataSrc.match(/\.(\w+)(?:\?|$)/);
+    if (urlMatch) return urlMatch[1];
+    return "png";
+  }
+
+  function handleDownload(e: MouseEvent) {
+    e.stopPropagation();
+    if (!src) return;
+    const link = document.createElement("a");
+    link.href = src;
+    link.download = `image-${Date.now()}.${extensionFromSrc(src)}`;
+    link.click();
+  }
+
+  function handleClose(e: MouseEvent) {
+    e.stopPropagation();
+    onclose();
+  }
+</script>
+
+<svelte:window onkeydown={src ? handleKeydown : undefined} />
+
+{#if src}
+  <div
+    class="fixed inset-0 z-50 bg-black/90 backdrop-blur-sm flex items-center justify-center"
+    transition:fade={{ duration: 200 }}
+    onclick={onclose}
+    role="presentation"
+    onintrostart={() => (document.body.style.overflow = "hidden")}
+    onoutroend={() => (document.body.style.overflow = "")}
+  >
+    <div class="absolute top-4 right-4 flex gap-2 z-10">
+      <button
+        type="button"
+        class="p-2 rounded-lg bg-exo-dark-gray/80 border border-exo-yellow/30 text-exo-yellow hover:bg-exo-dark-gray hover:border-exo-yellow/50 cursor-pointer transition-colors"
+        onclick={handleDownload}
+        title="Download image"
+      >
+        <svg
+          class="w-5 h-5"
+          fill="none"
+          viewBox="0 0 24 24"
+          stroke="currentColor"
+          stroke-width="2"
+        >
+          <path
+            stroke-linecap="round"
+            stroke-linejoin="round"
+            d="M4 16v1a3 3 0 003 3h10a3 3 0 003-3v-1m-4-4l-4 4m0 0l-4-4m4 4V4"
+          />
+        </svg>
+      </button>
+      <button
+        type="button"
+        class="p-2 rounded-lg bg-exo-dark-gray/80 border border-exo-yellow/30 text-exo-yellow hover:bg-exo-dark-gray hover:border-exo-yellow/50 cursor-pointer transition-colors"
+        onclick={handleClose}
+        title="Close"
+      >
+        <svg class="w-5 h-5" viewBox="0 0 24 24" fill="currentColor">
+          <path
+            d="M19 6.41L17.59 5 12 10.59 6.41 5 5 6.41 10.59 12 5 17.59 6.41 19 12 13.41 17.59 19 19 17.59 13.41 12 19 6.41z"
+          />
+        </svg>
+      </button>
+    </div>
+
+    <!-- svelte-ignore a11y_no_noninteractive_element_interactions, a11y_click_events_have_key_events -->
+    <img
+      {src}
+      alt=""
+      class="max-w-[90vw] max-h-[90vh] object-contain rounded-lg shadow-2xl"
+      transition:fly={{ y: 20, duration: 300, easing: cubicOut }}
+      onclick={(e) => e.stopPropagation()}
+    />
+  </div>
+{/if}

dashboard/src/lib/components/ImageParamsPanel.svelte

@@ -64,6 +64,8 @@
     "1024x1024",
     "1024x768",
     "768x1024",
+    "1024x1365",
+    "1365x1024",
   ];
 
   const qualityOptions: ImageGenerationParams["quality"][] = [
@@ -148,6 +150,15 @@
     setImageGenerationParams({ guidance: null });
   }
 
+  function handleNumSyncStepsChange(event: Event) {
+    const value = parseInt((event.target as HTMLInputElement).value, 10);
+    setImageGenerationParams({ numSyncSteps: value });
+  }
+
+  function clearNumSyncSteps() {
+    setImageGenerationParams({ numSyncSteps: null });
+  }
+
   function handleReset() {
     resetImageGenerationParams();
     showAdvanced = false;
@@ -157,7 +168,8 @@
     params.seed !== null ||
       params.numInferenceSteps !== null ||
       params.guidance !== null ||
-      (params.negativePrompt !== null && params.negativePrompt.trim() !== ""),
+      (params.negativePrompt !== null && params.negativePrompt.trim() !== "") ||
+      params.numSyncSteps !== null,
   );
 </script>
 
@@ -578,7 +590,50 @@
         </div>
       </div>
 
-      <!-- Row 3: Negative Prompt -->
+      <!-- Row 3: Sync Steps -->
+      <div class="flex items-center gap-1.5">
+        <span
+          class="text-xs text-exo-light-gray uppercase tracking-wider whitespace-nowrap"
+          >SYNC STEPS:</span
+        >
+        <div class="flex items-center gap-2 flex-1 max-w-xs">
+          <input
+            type="range"
+            min="1"
+            max="100"
+            value={params.numSyncSteps ?? 1}
+            oninput={handleNumSyncStepsChange}
+            class="flex-1 h-1 bg-exo-medium-gray/50 rounded appearance-none cursor-pointer accent-exo-yellow"
+          />
+          <span class="text-xs font-mono text-exo-yellow w-8 text-right">
+            {params.numSyncSteps ?? "--"}
+          </span>
+          {#if params.numSyncSteps !== null}
+            <button
+              type="button"
+              onclick={clearNumSyncSteps}
+              class="text-exo-light-gray hover:text-exo-yellow transition-colors"
+              title="Clear"
+            >
+              <svg
+                class="w-3 h-3"
+                fill="none"
+                viewBox="0 0 24 24"
+                stroke="currentColor"
+              >
+                <path
+                  stroke-linecap="round"
+                  stroke-linejoin="round"
+                  stroke-width="2"
+                  d="M6 18L18 6M6 6l12 12"
+                />
+              </svg>
+            </button>
+          {/if}
+        </div>
+      </div>
+
+      <!-- Row 4: Negative Prompt -->
       <div class="flex flex-col gap-1.5">
         <span class="text-xs text-exo-light-gray uppercase tracking-wider"
           >NEGATIVE PROMPT:</span

dashboard/src/lib/components/ModelCard.svelte

@@ -422,9 +422,16 @@
     const bToACandidates: Array<{ ip: string; iface: string | null }> = [];
 
     for (const edge of topology.edges) {
-      const ip = edge.sendBackIp || "?";
-      const iface =
-        edge.sendBackInterface || getInterfaceForIp(edge.source, ip);
+      let ip: string;
+      let iface: string | null;
+
+      if (edge.sourceRdmaIface || edge.sinkRdmaIface) {
+        ip = "RDMA";
+        iface = `${edge.sourceRdmaIface || "?"} \u2192 ${edge.sinkRdmaIface || "?"}`;
+      } else {
+        ip = edge.sendBackIp || "?";
+        iface = edge.sendBackInterface || getInterfaceForIp(edge.source, ip);
+      }
 
       if (edge.source === nodeId1 && edge.target === nodeId2) {
         aToBCandidates.push({ ip, iface });

dashboard/src/lib/components/ModelFilterPopover.svelte

@@ -0,0 +1,254 @@
+<script lang="ts">
+  import { fly } from "svelte/transition";
+  import { cubicOut } from "svelte/easing";
+
+  interface FilterState {
+    capabilities: string[];
+    sizeRange: { min: number; max: number } | null;
+    downloadedOnly: boolean;
+  }
+
+  type ModelFilterPopoverProps = {
+    filters: FilterState;
+    onChange: (filters: FilterState) => void;
+    onClear: () => void;
+    onClose: () => void;
+  };
+
+  let { filters, onChange, onClear, onClose }: ModelFilterPopoverProps =
+    $props();
+
+  // Available capabilities
+  const availableCapabilities = [
+    { id: "text", label: "Text" },
+    { id: "thinking", label: "Thinking" },
+    { id: "code", label: "Code" },
+    { id: "vision", label: "Vision" },
+    { id: "image_gen", label: "Image Gen" },
+    { id: "image_edit", label: "Image Edit" },
+  ];
+
+  // Size ranges
+  const sizeRanges = [
+    { label: "< 10GB", min: 0, max: 10 },
+    { label: "10-50GB", min: 10, max: 50 },
+    { label: "50-200GB", min: 50, max: 200 },
+    { label: "> 200GB", min: 200, max: 10000 },
+  ];
+
+  function toggleCapability(cap: string) {
+    const next = filters.capabilities.includes(cap)
+      ? filters.capabilities.filter((c) => c !== cap)
+      : [...filters.capabilities, cap];
+    onChange({ ...filters, capabilities: next });
+  }
+
+  function selectSizeRange(range: { min: number; max: number } | null) {
+    // Toggle off if same range is clicked
+    if (
+      filters.sizeRange &&
+      range &&
+      filters.sizeRange.min === range.min &&
+      filters.sizeRange.max === range.max
+    ) {
+      onChange({ ...filters, sizeRange: null });
+    } else {
+      onChange({ ...filters, sizeRange: range });
+    }
+  }
+
+  function handleClickOutside(e: MouseEvent) {
+    const target = e.target as HTMLElement;
+    if (
+      !target.closest(".filter-popover") &&
+      !target.closest(".filter-toggle")
+    ) {
+      onClose();
+    }
+  }
+</script>
+
+<svelte:window onclick={handleClickOutside} />
+
+<!-- svelte-ignore a11y_no_static_element_interactions -->
+<div
+  class="filter-popover absolute right-0 top-full mt-2 w-64 bg-exo-dark-gray border border-exo-yellow/10 rounded-lg shadow-xl z-10"
+  transition:fly={{ y: -10, duration: 200, easing: cubicOut }}
+  onclick={(e) => e.stopPropagation()}
+  role="dialog"
+  aria-label="Filter options"
+>
+  <div class="p-3 space-y-4">
+    <!-- Capabilities -->
+    <div>
+      <h4 class="text-xs font-mono text-white/50 mb-2">Capabilities</h4>
+      <div class="flex flex-wrap gap-1.5">
+        {#each availableCapabilities as cap}
+          {@const isSelected = filters.capabilities.includes(cap.id)}
+          <button
+            type="button"
+            class="px-2 py-1 text-xs font-mono rounded transition-colors {isSelected
+              ? 'bg-exo-yellow/20 text-exo-yellow border border-exo-yellow/30'
+              : 'bg-white/5 text-white/60 hover:bg-white/10 border border-transparent'}"
+            onclick={() => toggleCapability(cap.id)}
+          >
+            {#if cap.id === "text"}
+              <svg
+                class="w-3.5 h-3.5 inline-block"
+                viewBox="0 0 24 24"
+                fill="none"
+                stroke="currentColor"
+                stroke-width="1.5"
+                ><path
+                  d="M21 15a2 2 0 0 1-2 2H7l-4 4V5a2 2 0 0 1 2-2h14a2 2 0 0 1 2 2z"
+                  stroke-linecap="round"
+                  stroke-linejoin="round"
+                /></svg
+              >
+            {:else if cap.id === "thinking"}
+              <svg
+                class="w-3.5 h-3.5 inline-block"
+                viewBox="0 0 24 24"
+                fill="none"
+                stroke="currentColor"
+                stroke-width="1.5"
+                ><path
+                  d="M12 2a7 7 0 0 0-7 7c0 2.38 1.19 4.47 3 5.74V17a1 1 0 0 0 1 1h6a1 1 0 0 0 1-1v-2.26c1.81-1.27 3-3.36 3-5.74a7 7 0 0 0-7-7zM9 20h6M10 22h4"
+                  stroke-linecap="round"
+                  stroke-linejoin="round"
+                /></svg
+              >
+            {:else if cap.id === "code"}
+              <svg
+                class="w-3.5 h-3.5 inline-block"
+                viewBox="0 0 24 24"
+                fill="none"
+                stroke="currentColor"
+                stroke-width="1.5"
+                ><path
+                  d="M16 18l6-6-6-6M8 6l-6 6 6 6"
+                  stroke-linecap="round"
+                  stroke-linejoin="round"
+                /></svg
+              >
+            {:else if cap.id === "vision"}
+              <svg
+                class="w-3.5 h-3.5 inline-block"
+                viewBox="0 0 24 24"
+                fill="none"
+                stroke="currentColor"
+                stroke-width="1.5"
+                ><path
+                  d="M1 12s4-8 11-8 11 8 11 8-4 8-11 8-11-8-11-8z"
+                  stroke-linecap="round"
+                  stroke-linejoin="round"
+                /><circle cx="12" cy="12" r="3" /></svg
+              >
+            {:else if cap.id === "image_gen"}
+              <svg
+                class="w-3.5 h-3.5 inline-block"
+                viewBox="0 0 24 24"
+                fill="none"
+                stroke="currentColor"
+                stroke-width="1.5"
+                ><rect
+                  x="3"
+                  y="3"
+                  width="18"
+                  height="18"
+                  rx="2"
+                  ry="2"
+                  stroke-linecap="round"
+                  stroke-linejoin="round"
+                /><circle cx="8.5" cy="8.5" r="1.5" /><path
+                  d="M21 15l-5-5L5 21"
+                  stroke-linecap="round"
+                  stroke-linejoin="round"
+                /></svg
+              >
+            {:else if cap.id === "image_edit"}
+              <svg
+                class="w-3.5 h-3.5 inline-block"
+                viewBox="0 0 24 24"
+                fill="none"
+                stroke="currentColor"
+                stroke-width="1.5"
+                ><path
+                  d="M11 4H4a2 2 0 0 0-2 2v14a2 2 0 0 0 2 2h14a2 2 0 0 0 2-2v-7"
+                  stroke-linecap="round"
+                  stroke-linejoin="round"
+                /><path
+                  d="M18.5 2.5a2.121 2.121 0 0 1 3 3L12 15l-4 1 1-4 9.5-9.5z"
+                  stroke-linecap="round"
+                  stroke-linejoin="round"
+                /></svg
+              >
+            {/if}
+            <span class="ml-1">{cap.label}</span>
+          </button>
+        {/each}
+      </div>
+    </div>
+
+    <!-- Downloaded only -->
+    <div>
+      <h4 class="text-xs font-mono text-white/50 mb-2">Availability</h4>
+      <button
+        type="button"
+        class="px-2 py-1 text-xs font-mono rounded transition-colors {filters.downloadedOnly
+          ? 'bg-green-500/20 text-green-400 border border-green-500/30'
+          : 'bg-white/5 text-white/60 hover:bg-white/10 border border-transparent'}"
+        onclick={() =>
+          onChange({ ...filters, downloadedOnly: !filters.downloadedOnly })}
+      >
+        <svg
+          class="w-3.5 h-3.5 inline-block"
+          viewBox="0 0 24 24"
+          fill="none"
+          stroke="currentColor"
+          stroke-width="2"
+          stroke-linecap="round"
+          stroke-linejoin="round"
+        >
+          <path
+            class="text-white/40"
+            d="M20 20a2 2 0 0 0 2-2V8a2 2 0 0 0-2-2h-7.9a2 2 0 0 1-1.69-.9L9.6 3.9A2 2 0 0 0 7.93 3H4a2 2 0 0 0-2 2v13a2 2 0 0 0 2 2Z"
+          />
+          <path class="text-green-400" d="m9 13 2 2 4-4" />
+        </svg>
+        <span class="ml-1">Downloaded</span>
+      </button>
+    </div>
+
+    <!-- Size range -->
+    <div>
+      <h4 class="text-xs font-mono text-white/50 mb-2">Model Size</h4>
+      <div class="flex flex-wrap gap-1.5">
+        {#each sizeRanges as range}
+          {@const isSelected =
+            filters.sizeRange &&
+            filters.sizeRange.min === range.min &&
+            filters.sizeRange.max === range.max}
+          <button
+            type="button"
+            class="px-2 py-1 text-xs font-mono rounded transition-colors {isSelected
+              ? 'bg-exo-yellow/20 text-exo-yellow border border-exo-yellow/30'
+              : 'bg-white/5 text-white/60 hover:bg-white/10 border border-transparent'}"
+            onclick={() => selectSizeRange(range)}
+          >
+            {range.label}
+          </button>
+        {/each}
+      </div>
+    </div>
+
+    <!-- Clear button -->
+    <button
+      type="button"
+      class="w-full py-1.5 text-xs font-mono text-white/50 hover:text-white/70 hover:bg-white/5 rounded transition-colors"
+      onclick={onClear}
+    >
+      Clear all filters
+    </button>
+  </div>
+</div>

dashboard/src/lib/components/ModelPickerGroup.svelte

@@ -0,0 +1,497 @@
+<script lang="ts">
+  interface ModelInfo {
+    id: string;
+    name?: string;
+    storage_size_megabytes?: number;
+    base_model?: string;
+    quantization?: string;
+    supports_tensor?: boolean;
+    capabilities?: string[];
+    family?: string;
+    is_custom?: boolean;
+  }
+
+  interface ModelGroup {
+    id: string;
+    name: string;
+    capabilities: string[];
+    family: string;
+    variants: ModelInfo[];
+    smallestVariant: ModelInfo;
+    hasMultipleVariants: boolean;
+  }
+
+  type DownloadAvailability = {
+    available: boolean;
+    nodeNames: string[];
+    nodeIds: string[];
+  };
+  type ModelFitStatus = "fits_now" | "fits_cluster_capacity" | "too_large";
+
+  type ModelPickerGroupProps = {
+    group: ModelGroup;
+    isExpanded: boolean;
+    isFavorite: boolean;
+    selectedModelId: string | null;
+    canModelFit: (id: string) => boolean;
+    getModelFitStatus: (id: string) => ModelFitStatus;
+    onToggleExpand: () => void;
+    onSelectModel: (modelId: string) => void;
+    onToggleFavorite: (baseModelId: string) => void;
+    onShowInfo: (group: ModelGroup) => void;
+    downloadStatusMap?: Map<string, DownloadAvailability>;
+    launchedAt?: number;
+  };
+
+  let {
+    group,
+    isExpanded,
+    isFavorite,
+    selectedModelId,
+    canModelFit,
+    getModelFitStatus,
+    onToggleExpand,
+    onSelectModel,
+    onToggleFavorite,
+    onShowInfo,
+    downloadStatusMap,
+    launchedAt,
+  }: ModelPickerGroupProps = $props();
+
+  // Group-level download status: show if any variant is downloaded
+  const groupDownloadStatus = $derived.by(() => {
+    if (!downloadStatusMap || downloadStatusMap.size === 0) return undefined;
+    // Return the first available entry (prefer "available" ones)
+    for (const avail of downloadStatusMap.values()) {
+      if (avail.available) return avail;
+    }
+    return downloadStatusMap.values().next().value;
+  });
+
+  // Format storage size
+  function formatSize(mb: number | undefined): string {
+    if (!mb) return "";
+    if (mb >= 1024) {
+      return `${(mb / 1024).toFixed(0)}GB`;
+    }
+    return `${mb}MB`;
+  }
+
+  function timeAgo(ts: number): string {
+    const seconds = Math.floor((Date.now() - ts) / 1000);
+    if (seconds < 60) return "just now";
+    const minutes = Math.floor(seconds / 60);
+    if (minutes < 60) return `${minutes}m ago`;
+    const hours = Math.floor(minutes / 60);
+    if (hours < 24) return `${hours}h ago`;
+    const days = Math.floor(hours / 24);
+    return `${days}d ago`;
+  }
+
+  // Check if any variant can fit
+  const anyVariantFits = $derived(
+    group.variants.some((v) => canModelFit(v.id)),
+  );
+  const groupFitStatus = $derived.by((): ModelFitStatus => {
+    let hasClusterCapacityOnly = false;
+    for (const variant of group.variants) {
+      const fitStatus = getModelFitStatus(variant.id);
+      if (fitStatus === "fits_now") {
+        return "fits_now";
+      }
+      if (fitStatus === "fits_cluster_capacity") {
+        hasClusterCapacityOnly = true;
+      }
+    }
+    return hasClusterCapacityOnly ? "fits_cluster_capacity" : "too_large";
+  });
+
+  function getSizeClassForFitStatus(fitStatus: ModelFitStatus): string {
+    switch (fitStatus) {
+      case "fits_now":
+        return "text-white/40";
+      case "fits_cluster_capacity":
+        return "text-orange-400/80";
+      case "too_large":
+        return "text-red-400/70";
+    }
+  }
+
+  // Check if this group's model is currently selected (for single-variant groups)
+  const isMainSelected = $derived(
+    !group.hasMultipleVariants &&
+      group.variants.some((v) => v.id === selectedModelId),
+  );
+</script>
+
+<div
+  class="border-b border-white/5 last:border-b-0 {!anyVariantFits
+    ? 'opacity-50'
+    : ''}"
+>
+  <!-- Main row -->
+  <div
+    class="flex items-center gap-2 px-3 py-2.5 transition-colors {anyVariantFits
+      ? 'hover:bg-white/5 cursor-pointer'
+      : 'cursor-not-allowed'} {isMainSelected
+      ? 'bg-exo-yellow/10 border-l-2 border-exo-yellow'
+      : 'border-l-2 border-transparent'}"
+    onclick={() => {
+      if (group.hasMultipleVariants) {
+        onToggleExpand();
+      } else {
+        const modelId = group.variants[0]?.id;
+        if (modelId && canModelFit(modelId)) {
+          onSelectModel(modelId);
+        }
+      }
+    }}
+    role="button"
+    tabindex="0"
+    onkeydown={(e) => {
+      if (e.key === "Enter" || e.key === " ") {
+        e.preventDefault();
+        if (group.hasMultipleVariants) {
+          onToggleExpand();
+        } else {
+          const modelId = group.variants[0]?.id;
+          if (modelId && canModelFit(modelId)) {
+            onSelectModel(modelId);
+          }
+        }
+      }
+    }}
+  >
+    <!-- Expand/collapse chevron (for groups with variants) -->
+    {#if group.hasMultipleVariants}
+      <svg
+        class="w-4 h-4 text-white/40 transition-transform duration-200 flex-shrink-0 {isExpanded
+          ? 'rotate-90'
+          : ''}"
+        viewBox="0 0 24 24"
+        fill="currentColor"
+      >
+        <path d="M8.59 16.59L13.17 12 8.59 7.41 10 6l6 6-6 6-1.41-1.41z" />
+      </svg>
+    {:else}
+      <div class="w-4 flex-shrink-0"></div>
+    {/if}
+
+    <!-- Model name -->
+    <div class="flex-1 min-w-0">
+      <div class="flex items-center gap-2">
+        <span class="font-mono text-sm text-white truncate">
+          {group.name}
+        </span>
+        <!-- Capability icons -->
+        {#each group.capabilities.filter((c) => c !== "text") as cap}
+          {#if cap === "thinking"}
+            <svg
+              class="w-3.5 h-3.5 text-white/40 flex-shrink-0"
+              viewBox="0 0 24 24"
+              fill="none"
+              stroke="currentColor"
+              stroke-width="1.5"
+              title="Supports Thinking"
+            >
+              <path
+                d="M12 2a7 7 0 0 0-7 7c0 2.38 1.19 4.47 3 5.74V17a1 1 0 0 0 1 1h6a1 1 0 0 0 1-1v-2.26c1.81-1.27 3-3.36 3-5.74a7 7 0 0 0-7-7zM9 20h6M10 22h4"
+                stroke-linecap="round"
+                stroke-linejoin="round"
+              />
+            </svg>
+          {:else if cap === "code"}
+            <svg
+              class="w-3.5 h-3.5 text-white/40 flex-shrink-0"
+              viewBox="0 0 24 24"
+              fill="none"
+              stroke="currentColor"
+              stroke-width="1.5"
+              title="Supports code generation"
+            >
+              <path
+                d="M16 18l6-6-6-6M8 6l-6 6 6 6"
+                stroke-linecap="round"
+                stroke-linejoin="round"
+              />
+            </svg>
+          {:else if cap === "vision"}
+            <svg
+              class="w-3.5 h-3.5 text-white/40 flex-shrink-0"
+              viewBox="0 0 24 24"
+              fill="none"
+              stroke="currentColor"
+              stroke-width="1.5"
+              title="Supports image input"
+            >
+              <path
+                d="M1 12s4-8 11-8 11 8 11 8-4 8-11 8-11-8-11-8z"
+                stroke-linecap="round"
+                stroke-linejoin="round"
+              />
+              <circle cx="12" cy="12" r="3" />
+            </svg>
+          {:else if cap === "image_gen"}
+            <svg
+              class="w-3.5 h-3.5 text-white/40 flex-shrink-0"
+              viewBox="0 0 24 24"
+              fill="none"
+              stroke="currentColor"
+              stroke-width="1.5"
+              title="Supports image generation"
+            >
+              <rect
+                x="3"
+                y="3"
+                width="18"
+                height="18"
+                rx="2"
+                ry="2"
+                stroke-linecap="round"
+                stroke-linejoin="round"
+              />
+              <circle cx="8.5" cy="8.5" r="1.5" />
+              <path
+                d="M21 15l-5-5L5 21"
+                stroke-linecap="round"
+                stroke-linejoin="round"
+              />
+            </svg>
+          {:else if cap === "image_edit"}
+            <svg
+              class="w-3.5 h-3.5 text-white/40 flex-shrink-0"
+              viewBox="0 0 24 24"
+              fill="none"
+              stroke="currentColor"
+              stroke-width="1.5"
+              title="Supports image editing"
+            >
+              <path
+                d="M11 4H4a2 2 0 0 0-2 2v14a2 2 0 0 0 2 2h14a2 2 0 0 0 2-2v-7"
+                stroke-linecap="round"
+                stroke-linejoin="round"
+              />
+              <path
+                d="M18.5 2.5a2.121 2.121 0 0 1 3 3L12 15l-4 1 1-4 9.5-9.5z"
+                stroke-linecap="round"
+                stroke-linejoin="round"
+              />
+            </svg>
+          {/if}
+        {/each}
+      </div>
+    </div>
+
+    <!-- Size indicator (smallest variant) -->
+    {#if !group.hasMultipleVariants && group.smallestVariant?.storage_size_megabytes}
+      {@const singleVariantFitStatus = getModelFitStatus(
+        group.smallestVariant.id,
+      )}
+      <span
+        class="text-xs font-mono flex-shrink-0 {getSizeClassForFitStatus(
+          singleVariantFitStatus,
+        )}"
+      >
+        {formatSize(group.smallestVariant.storage_size_megabytes)}
+      </span>
+    {/if}
+
+    <!-- Variant count with size range -->
+    {#if group.hasMultipleVariants}
+      {@const sizes = group.variants
+        .map((v) => v.storage_size_megabytes || 0)
+        .filter((s) => s > 0)
+        .sort((a, b) => a - b)}
+      <span
+        class="text-xs font-mono flex-shrink-0 {getSizeClassForFitStatus(
+          groupFitStatus,
+        )}"
+      >
+        {group.variants.length} variants{#if sizes.length >= 2}{" "}({formatSize(
+            sizes[0],
+          )}-{formatSize(sizes[sizes.length - 1])}){/if}
+      </span>
+    {/if}
+
+    <!-- Time ago (for recent models) -->
+    {#if launchedAt}
+      <span class="text-xs font-mono text-white/20 flex-shrink-0">
+        {timeAgo(launchedAt)}
+      </span>
+    {/if}
+
+    <!-- Download availability indicator -->
+    {#if groupDownloadStatus && groupDownloadStatus.nodeIds.length > 0}
+      <span
+        class="flex-shrink-0"
+        title={groupDownloadStatus.available
+          ? `Ready — downloaded on ${groupDownloadStatus.nodeNames.join(", ")}`
+          : `Downloaded on ${groupDownloadStatus.nodeNames.join(", ")} (may need more nodes)`}
+      >
+        <svg
+          class="w-4 h-4"
+          viewBox="0 0 24 24"
+          fill="none"
+          stroke="currentColor"
+          stroke-width="2"
+          stroke-linecap="round"
+          stroke-linejoin="round"
+        >
+          <path
+            class="text-white/40"
+            d="M20 20a2 2 0 0 0 2-2V8a2 2 0 0 0-2-2h-7.9a2 2 0 0 1-1.69-.9L9.6 3.9A2 2 0 0 0 7.93 3H4a2 2 0 0 0-2 2v13a2 2 0 0 0 2 2Z"
+          />
+          <path class="text-green-400" d="m9 13 2 2 4-4" />
+        </svg>
+      </span>
+    {/if}
+
+    <!-- Check mark if selected (single-variant) -->
+    {#if isMainSelected}
+      <svg
+        class="w-4 h-4 text-exo-yellow flex-shrink-0"
+        viewBox="0 0 24 24"
+        fill="currentColor"
+      >
+        <path d="M9 16.17L4.83 12l-1.42 1.41L9 19 21 7l-1.41-1.41L9 16.17z" />
+      </svg>
+    {/if}
+
+    <!-- Favorite star -->
+    <button
+      type="button"
+      class="p-1 rounded hover:bg-white/10 transition-colors flex-shrink-0"
+      onclick={(e) => {
+        e.stopPropagation();
+        onToggleFavorite(group.id);
+      }}
+      title={isFavorite ? "Remove from favorites" : "Add to favorites"}
+    >
+      {#if isFavorite}
+        <svg
+          class="w-4 h-4 text-amber-400"
+          viewBox="0 0 24 24"
+          fill="currentColor"
+        >
+          <path
+            d="M12 2l3.09 6.26L22 9.27l-5 4.87 1.18 6.88L12 17.77l-6.18 3.25L7 14.14 2 9.27l6.91-1.01L12 2z"
+          />
+        </svg>
+      {:else}
+        <svg
+          class="w-4 h-4 text-white/30 hover:text-white/50"
+          viewBox="0 0 24 24"
+          fill="none"
+          stroke="currentColor"
+          stroke-width="2"
+        >
+          <path
+            d="M12 2l3.09 6.26L22 9.27l-5 4.87 1.18 6.88L12 17.77l-6.18 3.25L7 14.14 2 9.27l6.91-1.01L12 2z"
+          />
+        </svg>
+      {/if}
+    </button>
+
+    <!-- Info button -->
+    <button
+      type="button"
+      class="p-1 rounded hover:bg-white/10 transition-colors flex-shrink-0"
+      onclick={(e) => {
+        e.stopPropagation();
+        onShowInfo(group);
+      }}
+      title="View model details"
+    >
+      <svg
+        class="w-4 h-4 text-white/30 hover:text-white/50"
+        viewBox="0 0 24 24"
+        fill="currentColor"
+      >
+        <path
+          d="M12 2C6.48 2 2 6.48 2 12s4.48 10 10 10 10-4.48 10-10S17.52 2 12 2zm1 15h-2v-6h2v6zm0-8h-2V7h2v2z"
+        />
+      </svg>
+    </button>
+  </div>
+
+  <!-- Expanded variants -->
+  {#if isExpanded && group.hasMultipleVariants}
+    <div class="bg-black/20 border-t border-white/5">
+      {#each group.variants as variant}
+        {@const fitStatus = getModelFitStatus(variant.id)}
+        {@const modelCanFit = canModelFit(variant.id)}
+        {@const isSelected = selectedModelId === variant.id}
+        <button
+          type="button"
+          class="w-full flex items-center gap-3 px-3 py-2 pl-10 hover:bg-white/5 transition-colors text-left {!modelCanFit
+            ? 'opacity-50 cursor-not-allowed'
+            : 'cursor-pointer'} {isSelected
+            ? 'bg-exo-yellow/10 border-l-2 border-exo-yellow'
+            : 'border-l-2 border-transparent'}"
+          disabled={!modelCanFit}
+          onclick={() => {
+            if (modelCanFit) {
+              onSelectModel(variant.id);
+            }
+          }}
+        >
+          <!-- Quantization badge -->
+          <span
+            class="text-xs font-mono px-1.5 py-0.5 rounded bg-white/10 text-white/70 flex-shrink-0"
+          >
+            {variant.quantization || "default"}
+          </span>
+
+          <!-- Size -->
+          <span
+            class="text-xs font-mono flex-1 {getSizeClassForFitStatus(
+              fitStatus,
+            )}"
+          >
+            {formatSize(variant.storage_size_megabytes)}
+          </span>
+
+          <!-- Download indicator for this variant -->
+          {#if downloadStatusMap?.get(variant.id)}
+            {@const variantDl = downloadStatusMap.get(variant.id)}
+            {#if variantDl}
+              <span
+                class="flex-shrink-0"
+                title={`Downloaded on ${variantDl.nodeNames.join(", ")}`}
+              >
+                <svg
+                  class="w-3.5 h-3.5"
+                  viewBox="0 0 24 24"
+                  fill="none"
+                  stroke="currentColor"
+                  stroke-width="2"
+                  stroke-linecap="round"
+                  stroke-linejoin="round"
+                >
+                  <path
+                    class="text-white/40"
+                    d="M20 20a2 2 0 0 0 2-2V8a2 2 0 0 0-2-2h-7.9a2 2 0 0 1-1.69-.9L9.6 3.9A2 2 0 0 0 7.93 3H4a2 2 0 0 0-2 2v13a2 2 0 0 0 2 2Z"
+                  />
+                  <path class="text-green-400" d="m9 13 2 2 4-4" />
+                </svg>
+              </span>
+            {/if}
+          {/if}
+
+          <!-- Check mark if selected -->
+          {#if isSelected}
+            <svg
+              class="w-4 h-4 text-exo-yellow"
+              viewBox="0 0 24 24"
+              fill="currentColor"
+            >
+              <path
+                d="M9 16.17L4.83 12l-1.42 1.41L9 19 21 7l-1.41-1.41L9 16.17z"
+              />
+            </svg>
+          {/if}
+        </button>
+      {/each}
+    </div>
+  {/if}
+</div>

dashboard/src/lib/components/ModelPickerModal.svelte

@@ -0,0 +1,990 @@
+<script lang="ts">
+  import { fade, fly } from "svelte/transition";
+  import { cubicOut } from "svelte/easing";
+  import FamilySidebar from "./FamilySidebar.svelte";
+  import ModelPickerGroup from "./ModelPickerGroup.svelte";
+  import ModelFilterPopover from "./ModelFilterPopover.svelte";
+  import HuggingFaceResultItem from "./HuggingFaceResultItem.svelte";
+  import { getNodesWithModelDownloaded } from "$lib/utils/downloads";
+  import { getRecentEntries } from "$lib/stores/recents.svelte";
+
+  interface ModelInfo {
+    id: string;
+    name?: string;
+    storage_size_megabytes?: number;
+    base_model?: string;
+    quantization?: string;
+    supports_tensor?: boolean;
+    capabilities?: string[];
+    family?: string;
+    is_custom?: boolean;
+    tasks?: string[];
+    hugging_face_id?: string;
+  }
+
+  interface ModelGroup {
+    id: string;
+    name: string;
+    capabilities: string[];
+    family: string;
+    variants: ModelInfo[];
+    smallestVariant: ModelInfo;
+    hasMultipleVariants: boolean;
+  }
+
+  interface FilterState {
+    capabilities: string[];
+    sizeRange: { min: number; max: number } | null;
+    downloadedOnly: boolean;
+  }
+
+  interface HuggingFaceModel {
+    id: string;
+    author: string;
+    downloads: number;
+    likes: number;
+    last_modified: string;
+    tags: string[];
+  }
+
+  type ModelFitStatus = "fits_now" | "fits_cluster_capacity" | "too_large";
+
+  type ModelPickerModalProps = {
+    isOpen: boolean;
+    models: ModelInfo[];
+    selectedModelId: string | null;
+    favorites: Set<string>;
+    recentModelIds?: string[];
+    hasRecents?: boolean;
+    existingModelIds: Set<string>;
+    canModelFit: (modelId: string) => boolean;
+    getModelFitStatus: (modelId: string) => ModelFitStatus;
+    onSelect: (modelId: string) => void;
+    onClose: () => void;
+    onToggleFavorite: (baseModelId: string) => void;
+    onAddModel: (modelId: string) => Promise<void>;
+    onDeleteModel: (modelId: string) => Promise<void>;
+    totalMemoryGB: number;
+    usedMemoryGB: number;
+    downloadsData?: Record<string, unknown[]>;
+    topologyNodes?: Record<
+      string,
+      {
+        friendly_name?: string;
+        system_info?: { model_id?: string };
+        macmon_info?: { memory?: { ram_total?: number } };
+      }
+    >;
+  };
+
+  let {
+    isOpen,
+    models,
+    selectedModelId,
+    favorites,
+    recentModelIds = [],
+    hasRecents: hasRecentsTab = false,
+    existingModelIds,
+    canModelFit,
+    getModelFitStatus,
+    onSelect,
+    onClose,
+    onToggleFavorite,
+    onAddModel,
+    onDeleteModel,
+    totalMemoryGB,
+    usedMemoryGB,
+    downloadsData,
+    topologyNodes,
+  }: ModelPickerModalProps = $props();
+
+  // Local state
+  let searchQuery = $state("");
+  let selectedFamily = $state<string | null>(null);
+  let expandedGroups = $state<Set<string>>(new Set());
+  let showFilters = $state(false);
+  let filters = $state<FilterState>({
+    capabilities: [],
+    sizeRange: null,
+    downloadedOnly: false,
+  });
+  let infoGroup = $state<ModelGroup | null>(null);
+
+  // Download availability per model group
+  type DownloadAvailability = {
+    available: boolean;
+    nodeNames: string[];
+    nodeIds: string[];
+  };
+
+  function getNodeName(nodeId: string): string {
+    const node = topologyNodes?.[nodeId];
+    return (
+      node?.friendly_name || node?.system_info?.model_id || nodeId.slice(0, 8)
+    );
+  }
+
+  const modelDownloadAvailability = $derived.by(() => {
+    const result = new Map<string, DownloadAvailability>();
+    if (!downloadsData || !topologyNodes) return result;
+
+    for (const model of models) {
+      const nodeIds = getNodesWithModelDownloaded(downloadsData, model.id);
+      if (nodeIds.length === 0) continue;
+
+      // Sum total RAM across nodes that have the model
+      let totalRamBytes = 0;
+      for (const nodeId of nodeIds) {
+        const ramTotal = topologyNodes[nodeId]?.macmon_info?.memory?.ram_total;
+        if (typeof ramTotal === "number") totalRamBytes += ramTotal;
+      }
+
+      const modelSizeBytes = (model.storage_size_megabytes || 0) * 1024 * 1024;
+      result.set(model.id, {
+        available: modelSizeBytes > 0 && totalRamBytes >= modelSizeBytes,
+        nodeNames: nodeIds.map(getNodeName),
+        nodeIds,
+      });
+    }
+    return result;
+  });
+
+  // Aggregate download availability per group (available if ANY variant is available)
+  function getGroupDownloadAvailability(
+    group: ModelGroup,
+  ): DownloadAvailability | undefined {
+    for (const variant of group.variants) {
+      const avail = modelDownloadAvailability.get(variant.id);
+      if (avail && avail.nodeIds.length > 0) return avail;
+    }
+    return undefined;
+  }
+
+  // Get per-variant download map for a group
+  function getVariantDownloadMap(
+    group: ModelGroup,
+  ): Map<string, DownloadAvailability> {
+    const map = new Map<string, DownloadAvailability>();
+    for (const variant of group.variants) {
+      const avail = modelDownloadAvailability.get(variant.id);
+      if (avail && avail.nodeIds.length > 0) map.set(variant.id, avail);
+    }
+    return map;
+  }
+
+  // HuggingFace Hub state
+  let hfSearchQuery = $state("");
+  let hfSearchResults = $state<HuggingFaceModel[]>([]);
+  let hfTrendingModels = $state<HuggingFaceModel[]>([]);
+  let hfIsSearching = $state(false);
+  let hfIsLoadingTrending = $state(false);
+  let addingModelId = $state<string | null>(null);
+  let hfSearchDebounceTimer: ReturnType<typeof setTimeout> | null = null;
+  let manualModelId = $state("");
+  let addModelError = $state<string | null>(null);
+
+  // Reset transient state when modal opens, but preserve tab selection
+  $effect(() => {
+    if (isOpen) {
+      searchQuery = "";
+      expandedGroups = new Set();
+      showFilters = false;
+      manualModelId = "";
+      addModelError = null;
+    }
+  });
+
+  // Fetch trending models when HuggingFace is selected
+  $effect(() => {
+    if (
+      selectedFamily === "huggingface" &&
+      hfTrendingModels.length === 0 &&
+      !hfIsLoadingTrending
+    ) {
+      fetchTrendingModels();
+    }
+  });
+
+  async function fetchTrendingModels() {
+    hfIsLoadingTrending = true;
+    try {
+      const response = await fetch("/models/search?query=&limit=20");
+      if (response.ok) {
+        hfTrendingModels = await response.json();
+      }
+    } catch (error) {
+      console.error("Failed to fetch trending models:", error);
+    } finally {
+      hfIsLoadingTrending = false;
+    }
+  }
+
+  async function searchHuggingFace(query: string) {
+    if (query.length < 2) {
+      hfSearchResults = [];
+      return;
+    }
+
+    hfIsSearching = true;
+    try {
+      const response = await fetch(
+        `/models/search?query=${encodeURIComponent(query)}&limit=20`,
+      );
+      if (response.ok) {
+        hfSearchResults = await response.json();
+      } else {
+        hfSearchResults = [];
+      }
+    } catch (error) {
+      console.error("Failed to search models:", error);
+      hfSearchResults = [];
+    } finally {
+      hfIsSearching = false;
+    }
+  }
+
+  function handleHfSearchInput(query: string) {
+    hfSearchQuery = query;
+    addModelError = null;
+
+    if (hfSearchDebounceTimer) {
+      clearTimeout(hfSearchDebounceTimer);
+    }
+
+    if (query.length >= 2) {
+      hfSearchDebounceTimer = setTimeout(() => {
+        searchHuggingFace(query);
+      }, 300);
+    } else {
+      hfSearchResults = [];
+    }
+  }
+
+  async function handleAddModel(modelId: string) {
+    addingModelId = modelId;
+    addModelError = null;
+    try {
+      await onAddModel(modelId);
+    } catch (error) {
+      addModelError =
+        error instanceof Error ? error.message : "Failed to add model";
+    } finally {
+      addingModelId = null;
+    }
+  }
+
+  async function handleAddManualModel() {
+    if (!manualModelId.trim()) return;
+    await handleAddModel(manualModelId.trim());
+    if (!addModelError) {
+      manualModelId = "";
+    }
+  }
+
+  function handleSelectHfModel(modelId: string) {
+    onSelect(modelId);
+    onClose();
+  }
+
+  // Models to display in HuggingFace view
+  const hfDisplayModels = $derived.by((): HuggingFaceModel[] => {
+    if (hfSearchQuery.length >= 2) {
+      return hfSearchResults;
+    }
+    return hfTrendingModels;
+  });
+
+  // Group models by base_model
+  const groupedModels = $derived.by((): ModelGroup[] => {
+    const groups = new Map<string, ModelGroup>();
+
+    for (const model of models) {
+      const groupId = model.base_model || model.id;
+      const groupName = model.base_model || model.name || model.id;
+
+      if (!groups.has(groupId)) {
+        groups.set(groupId, {
+          id: groupId,
+          name: groupName,
+          capabilities: model.capabilities || ["text"],
+          family: model.family || "",
+          variants: [],
+          smallestVariant: model,
+          hasMultipleVariants: false,
+        });
+      }
+
+      const group = groups.get(groupId)!;
+      group.variants.push(model);
+
+      // Track smallest variant
+      if (
+        (model.storage_size_megabytes || 0) <
+        (group.smallestVariant.storage_size_megabytes || Infinity)
+      ) {
+        group.smallestVariant = model;
+      }
+
+      // Update capabilities if not set
+      if (
+        group.capabilities.length <= 1 &&
+        model.capabilities &&
+        model.capabilities.length > 1
+      ) {
+        group.capabilities = model.capabilities;
+      }
+      if (!group.family && model.family) {
+        group.family = model.family;
+      }
+    }
+
+    // Sort variants within each group by size
+    for (const group of groups.values()) {
+      group.variants.sort(
+        (a, b) =>
+          (a.storage_size_megabytes || 0) - (b.storage_size_megabytes || 0),
+      );
+      group.hasMultipleVariants = group.variants.length > 1;
+    }
+
+    // Convert to array and sort by smallest variant size (biggest first)
+    return Array.from(groups.values()).sort((a, b) => {
+      return (
+        (b.smallestVariant.storage_size_megabytes || 0) -
+        (a.smallestVariant.storage_size_megabytes || 0)
+      );
+    });
+  });
+
+  // Get unique families
+  const uniqueFamilies = $derived.by((): string[] => {
+    const families = new Set<string>();
+    for (const group of groupedModels) {
+      if (group.family) {
+        families.add(group.family);
+      }
+    }
+    const familyOrder = [
+      "kimi",
+      "qwen",
+      "glm",
+      "minimax",
+      "deepseek",
+      "gpt-oss",
+      "llama",
+      "flux",
+      "qwen-image",
+    ];
+    return Array.from(families).sort((a, b) => {
+      const aIdx = familyOrder.indexOf(a);
+      const bIdx = familyOrder.indexOf(b);
+      if (aIdx === -1 && bIdx === -1) return a.localeCompare(b);
+      if (aIdx === -1) return 1;
+      if (bIdx === -1) return -1;
+      return aIdx - bIdx;
+    });
+  });
+
+  // Filter models based on search, family, and filters
+  const filteredGroups = $derived.by((): ModelGroup[] => {
+    let result: ModelGroup[] = [...groupedModels];
+
+    // Filter by family
+    if (selectedFamily === "favorites") {
+      result = result.filter((g) => favorites.has(g.id));
+    } else if (
+      selectedFamily &&
+      selectedFamily !== "huggingface" &&
+      selectedFamily !== "recents"
+    ) {
+      result = result.filter((g) => g.family === selectedFamily);
+    }
+
+    // Filter by search query
+    if (searchQuery.trim()) {
+      const query = searchQuery.toLowerCase().trim();
+      result = result.filter(
+        (g) =>
+          g.name.toLowerCase().includes(query) ||
+          g.variants.some(
+            (v) =>
+              v.id.toLowerCase().includes(query) ||
+              (v.name || "").toLowerCase().includes(query),
+          ),
+      );
+    }
+
+    // Filter by capabilities
+    if (filters.capabilities.length > 0) {
+      result = result.filter((g) =>
+        filters.capabilities.every((cap) => g.capabilities.includes(cap)),
+      );
+    }
+
+    // Filter by size range
+    if (filters.sizeRange) {
+      const { min, max } = filters.sizeRange;
+      result = result.filter((g) => {
+        const sizeGB = (g.smallestVariant.storage_size_megabytes || 0) / 1024;
+        return sizeGB >= min && sizeGB <= max;
+      });
+    }
+
+    // Filter to downloaded models only
+    if (filters.downloadedOnly) {
+      result = result.filter((g) =>
+        g.variants.some((v) => {
+          const avail = modelDownloadAvailability.get(v.id);
+          return avail && avail.nodeIds.length > 0;
+        }),
+      );
+    }
+
+    // Sort: fits-now first, then fits-cluster-capacity, then too-large
+    result.sort((a, b) => {
+      const getGroupFitRank = (group: ModelGroup): number => {
+        let hasClusterCapacityOnly = false;
+        for (const variant of group.variants) {
+          const fitStatus = getModelFitStatus(variant.id);
+          if (fitStatus === "fits_now") return 0;
+          if (fitStatus === "fits_cluster_capacity") {
+            hasClusterCapacityOnly = true;
+          }
+        }
+        return hasClusterCapacityOnly ? 1 : 2;
+      };
+
+      const aRank = getGroupFitRank(a);
+      const bRank = getGroupFitRank(b);
+      if (aRank !== bRank) return aRank - bRank;
+
+      return (
+        (b.smallestVariant.storage_size_megabytes || 0) -
+        (a.smallestVariant.storage_size_megabytes || 0)
+      );
+    });
+
+    return result;
+  });
+
+  // Check if any favorites exist
+  const hasFavorites = $derived(favorites.size > 0);
+
+  // Timestamp lookup for recent models
+  const recentTimestamps = $derived(
+    new Map(getRecentEntries().map((e) => [e.modelId, e.launchedAt])),
+  );
+
+  // Recent models: single-variant ModelGroups in launch order
+  const recentGroups = $derived.by((): ModelGroup[] => {
+    if (!recentModelIds || recentModelIds.length === 0) return [];
+    const result: ModelGroup[] = [];
+    for (const id of recentModelIds) {
+      const model = models.find((m) => m.id === id);
+      if (model) {
+        result.push({
+          id: model.base_model || model.id,
+          name: model.name || model.id,
+          capabilities: model.capabilities || ["text"],
+          family: model.family || "",
+          variants: [model],
+          smallestVariant: model,
+          hasMultipleVariants: false,
+        });
+      }
+    }
+    return result;
+  });
+
+  // Filtered recent groups (apply search query)
+  const filteredRecentGroups = $derived.by((): ModelGroup[] => {
+    if (!searchQuery.trim()) return recentGroups;
+    const query = searchQuery.toLowerCase().trim();
+    return recentGroups.filter(
+      (g) =>
+        g.name.toLowerCase().includes(query) ||
+        g.variants.some(
+          (v) =>
+            v.id.toLowerCase().includes(query) ||
+            (v.name || "").toLowerCase().includes(query) ||
+            (v.quantization || "").toLowerCase().includes(query),
+        ),
+    );
+  });
+
+  function toggleGroupExpanded(groupId: string) {
+    const next = new Set(expandedGroups);
+    if (next.has(groupId)) {
+      next.delete(groupId);
+    } else {
+      next.add(groupId);
+    }
+    expandedGroups = next;
+  }
+
+  function handleSelect(modelId: string) {
+    onSelect(modelId);
+    onClose();
+  }
+
+  function handleKeydown(e: KeyboardEvent) {
+    if (e.key === "Escape") {
+      onClose();
+    }
+  }
+
+  function handleFiltersChange(newFilters: FilterState) {
+    filters = newFilters;
+  }
+
+  function clearFilters() {
+    filters = { capabilities: [], sizeRange: null, downloadedOnly: false };
+  }
+
+  const hasActiveFilters = $derived(
+    filters.capabilities.length > 0 ||
+      filters.sizeRange !== null ||
+      filters.downloadedOnly,
+  );
+</script>
+
+<svelte:window onkeydown={handleKeydown} />
+
+{#if isOpen}
+  <!-- Backdrop -->
+  <div
+    class="fixed inset-0 z-50 bg-black/80 backdrop-blur-sm"
+    transition:fade={{ duration: 200 }}
+    onclick={onClose}
+    role="presentation"
+  ></div>
+
+  <!-- Modal -->
+  <div
+    class="fixed z-50 top-1/2 left-1/2 -translate-x-1/2 -translate-y-1/2 w-[min(90vw,600px)] h-[min(80vh,700px)] bg-exo-dark-gray border border-exo-yellow/10 rounded-lg shadow-2xl overflow-hidden flex flex-col"
+    transition:fly={{ y: 20, duration: 300, easing: cubicOut }}
+    role="dialog"
+    aria-modal="true"
+    aria-label="Select a model"
+  >
+    <!-- Header with search -->
+    <div
+      class="flex items-center gap-2 p-3 border-b border-exo-yellow/10 bg-exo-medium-gray/30"
+    >
+      {#if selectedFamily === "huggingface"}
+        <!-- HuggingFace search -->
+        <svg
+          class="w-5 h-5 text-orange-400/60 flex-shrink-0"
+          viewBox="0 0 24 24"
+          fill="none"
+          stroke="currentColor"
+          stroke-width="2"
+        >
+          <circle cx="11" cy="11" r="8" />
+          <path d="M21 21l-4.35-4.35" />
+        </svg>
+        <input
+          type="search"
+          class="flex-1 bg-transparent border-none outline-none text-sm font-mono text-white placeholder-white/40"
+          placeholder="Search mlx-community models..."
+          value={hfSearchQuery}
+          oninput={(e) => handleHfSearchInput(e.currentTarget.value)}
+        />
+        {#if hfIsSearching}
+          <div class="flex-shrink-0">
+            <span
+              class="w-4 h-4 border-2 border-orange-400 border-t-transparent rounded-full animate-spin block"
+            ></span>
+          </div>
+        {/if}
+      {:else}
+        <!-- Normal model search -->
+        <svg
+          class="w-5 h-5 text-white/40 flex-shrink-0"
+          viewBox="0 0 24 24"
+          fill="none"
+          stroke="currentColor"
+          stroke-width="2"
+        >
+          <circle cx="11" cy="11" r="8" />
+          <path d="M21 21l-4.35-4.35" />
+        </svg>
+        <input
+          type="search"
+          class="flex-1 bg-transparent border-none outline-none text-sm font-mono text-white placeholder-white/40"
+          placeholder="Search models..."
+          bind:value={searchQuery}
+        />
+        <!-- Cluster memory -->
+        <span
+          class="text-xs font-mono flex-shrink-0"
+          title="Cluster memory usage"
+          ><span class="text-exo-yellow">{Math.round(usedMemoryGB)}GB</span
+          ><span class="text-white/40">/{Math.round(totalMemoryGB)}GB</span
+          ></span
+        >
+        <!-- Filter button -->
+        <div class="relative filter-toggle">
+          <button
+            type="button"
+            class="p-1.5 rounded hover:bg-white/10 transition-colors {hasActiveFilters
+              ? 'text-exo-yellow'
+              : 'text-white/50'}"
+            onclick={() => (showFilters = !showFilters)}
+            title="Filter by capability or size"
+          >
+            <svg class="w-5 h-5" viewBox="0 0 24 24" fill="currentColor">
+              <path d="M10 18h4v-2h-4v2zM3 6v2h18V6H3zm3 7h12v-2H6v2z" />
+            </svg>
+          </button>
+          {#if showFilters}
+            <ModelFilterPopover
+              {filters}
+              onChange={handleFiltersChange}
+              onClear={clearFilters}
+              onClose={() => (showFilters = false)}
+            />
+          {/if}
+        </div>
+      {/if}
+      <!-- Close button -->
+      <button
+        type="button"
+        class="p-1.5 rounded hover:bg-white/10 transition-colors text-white/50 hover:text-white/70"
+        onclick={onClose}
+        title="Close model picker"
+      >
+        <svg class="w-5 h-5" viewBox="0 0 24 24" fill="currentColor">
+          <path
+            d="M19 6.41L17.59 5 12 10.59 6.41 5 5 6.41 10.59 12 5 17.59 6.41 19 12 13.41 17.59 19 19 17.59 13.41 12 19 6.41z"
+          />
+        </svg>
+      </button>
+    </div>
+
+    <!-- Body -->
+    <div class="flex flex-1 overflow-hidden">
+      <!-- Family sidebar -->
+      <FamilySidebar
+        families={uniqueFamilies}
+        {selectedFamily}
+        {hasFavorites}
+        hasRecents={hasRecentsTab}
+        onSelect={(family) => (selectedFamily = family)}
+      />
+
+      <!-- Model list -->
+      <div class="flex-1 overflow-y-auto scrollbar-hide flex flex-col">
+        {#if selectedFamily === "huggingface"}
+          <!-- HuggingFace Hub view -->
+          <div class="flex-1 flex flex-col min-h-0">
+            <!-- Section header -->
+            <div
+              class="sticky top-0 z-10 px-3 py-2 bg-exo-dark-gray/95 border-b border-exo-yellow/10"
+            >
+              <span class="text-xs font-mono text-white/40">
+                {#if hfSearchQuery.length >= 2}
+                  Search results for "{hfSearchQuery}"
+                {:else}
+                  Trending on mlx-community
+                {/if}
+              </span>
+            </div>
+
+            <!-- Results list -->
+            <div class="flex-1 overflow-y-auto scrollbar-hide">
+              {#if hfIsLoadingTrending && hfTrendingModels.length === 0}
+                <div
+                  class="flex items-center justify-center py-12 text-white/40"
+                >
+                  <span
+                    class="w-5 h-5 border-2 border-orange-400 border-t-transparent rounded-full animate-spin mr-2"
+                  ></span>
+                  <span class="font-mono text-sm"
+                    >Loading trending models...</span
+                  >
+                </div>
+              {:else if hfDisplayModels.length === 0}
+                <div
+                  class="flex flex-col items-center justify-center py-12 text-white/40"
+                >
+                  <svg
+                    class="w-10 h-10 mb-2"
+                    viewBox="0 0 24 24"
+                    fill="currentColor"
+                  >
+                    <path
+                      d="M12 2C6.48 2 2 6.48 2 12s4.48 10 10 10 10-4.48 10-10S17.52 2 12 2zm-2 13.5c-.83 0-1.5-.67-1.5-1.5s.67-1.5 1.5-1.5 1.5.67 1.5 1.5-.67 1.5-1.5 1.5zm4 0c-.83 0-1.5-.67-1.5-1.5s.67-1.5 1.5-1.5 1.5.67 1.5 1.5-.67 1.5-1.5 1.5zm2-4.5H8c0-2.21 1.79-4 4-4s4 1.79 4 4z"
+                    />
+                  </svg>
+                  <p class="font-mono text-sm">No models found</p>
+                  {#if hfSearchQuery}
+                    <p class="font-mono text-xs mt-1">
+                      Try a different search term
+                    </p>
+                  {/if}
+                </div>
+              {:else}
+                {#each hfDisplayModels as model}
+                  <HuggingFaceResultItem
+                    {model}
+                    isAdded={existingModelIds.has(model.id)}
+                    isAdding={addingModelId === model.id}
+                    onAdd={() => handleAddModel(model.id)}
+                    onSelect={() => handleSelectHfModel(model.id)}
+                    downloadedOnNodes={downloadsData
+                      ? getNodesWithModelDownloaded(
+                          downloadsData,
+                          model.id,
+                        ).map(getNodeName)
+                      : []}
+                  />
+                {/each}
+              {/if}
+            </div>
+
+            <!-- Manual input footer -->
+            <div
+              class="sticky bottom-0 border-t border-exo-yellow/10 bg-exo-dark-gray p-3"
+            >
+              {#if addModelError}
+                <div
+                  class="bg-red-500/10 border border-red-500/30 rounded px-3 py-2 mb-2"
+                >
+                  <p class="text-red-400 text-xs font-mono break-words">
+                    {addModelError}
+                  </p>
+                </div>
+              {/if}
+              <div class="flex gap-2">
+                <input
+                  type="text"
+                  class="flex-1 bg-exo-black/60 border border-exo-yellow/30 rounded px-3 py-1.5 text-xs font-mono text-white placeholder-white/30 focus:outline-none focus:border-exo-yellow/50"
+                  placeholder="Or paste model ID directly..."
+                  bind:value={manualModelId}
+                  onkeydown={(e) => {
+                    if (e.key === "Enter") handleAddManualModel();
+                  }}
+                />
+                <button
+                  type="button"
+                  onclick={handleAddManualModel}
+                  disabled={!manualModelId.trim() || addingModelId !== null}
+                  class="px-3 py-1.5 text-xs font-mono tracking-wider uppercase bg-orange-500/10 text-orange-400 border border-orange-400/30 hover:bg-orange-500/20 transition-colors rounded disabled:opacity-50 disabled:cursor-not-allowed"
+                >
+                  Add
+                </button>
+              </div>
+            </div>
+          </div>
+        {:else if selectedFamily === "recents"}
+          <!-- Recent models view -->
+          {#if filteredRecentGroups.length === 0}
+            <div
+              class="flex flex-col items-center justify-center h-full text-white/40 p-8"
+            >
+              <svg
+                class="w-12 h-12 mb-3"
+                viewBox="0 0 24 24"
+                fill="currentColor"
+              >
+                <path
+                  d="M13 3a9 9 0 0 0-9 9H1l3.89 3.89.07.14L9 12H6c0-3.87 3.13-7 7-7s7 3.13 7 7-3.13 7-7 7c-1.93 0-3.68-.79-4.94-2.06l-1.42 1.42A8.954 8.954 0 0 0 13 21a9 9 0 0 0 0-18zm-1 5v5l4.28 2.54.72-1.21-3.5-2.08V8H12z"
+                />
+              </svg>
+              <p class="font-mono text-sm">
+                {searchQuery
+                  ? "No matching recent models"
+                  : "No recently launched models"}
+              </p>
+            </div>
+          {:else}
+            {#each filteredRecentGroups as group}
+              <ModelPickerGroup
+                {group}
+                isExpanded={expandedGroups.has(group.id)}
+                isFavorite={favorites.has(group.id)}
+                {selectedModelId}
+                {canModelFit}
+                {getModelFitStatus}
+                onToggleExpand={() => toggleGroupExpanded(group.id)}
+                onSelectModel={handleSelect}
+                {onToggleFavorite}
+                onShowInfo={(g) => (infoGroup = g)}
+                downloadStatusMap={getVariantDownloadMap(group)}
+                launchedAt={recentTimestamps.get(group.variants[0]?.id ?? "")}
+              />
+            {/each}
+          {/if}
+        {:else if filteredGroups.length === 0}
+          <div
+            class="flex flex-col items-center justify-center h-full text-white/40 p-8"
+          >
+            <svg class="w-12 h-12 mb-3" viewBox="0 0 24 24" fill="currentColor">
+              <path
+                d="M12 2C6.48 2 2 6.48 2 12s4.48 10 10 10 10-4.48 10-10S17.52 2 12 2zm-2 15l-5-5 1.41-1.41L10 14.17l7.59-7.59L19 8l-9 9z"
+              />
+            </svg>
+            <p class="font-mono text-sm">No models found</p>
+            {#if hasActiveFilters || searchQuery}
+              <button
+                type="button"
+                class="mt-2 text-xs text-exo-yellow hover:underline"
+                onclick={() => {
+                  searchQuery = "";
+                  clearFilters();
+                }}
+              >
+                Clear filters
+              </button>
+            {/if}
+          </div>
+        {:else}
+          {#each filteredGroups as group}
+            <ModelPickerGroup
+              {group}
+              isExpanded={expandedGroups.has(group.id)}
+              isFavorite={favorites.has(group.id)}
+              {selectedModelId}
+              {canModelFit}
+              {getModelFitStatus}
+              onToggleExpand={() => toggleGroupExpanded(group.id)}
+              onSelectModel={handleSelect}
+              {onToggleFavorite}
+              onShowInfo={(g) => (infoGroup = g)}
+              downloadStatusMap={getVariantDownloadMap(group)}
+            />
+          {/each}
+        {/if}
+      </div>
+    </div>
+
+    <!-- Footer with active filters indicator -->
+    {#if hasActiveFilters}
+      <div
+        class="flex items-center gap-2 px-3 py-2 border-t border-exo-yellow/10 bg-exo-medium-gray/20 text-xs font-mono text-white/50"
+      >
+        <span>Filters:</span>
+        {#each filters.capabilities as cap}
+          <span class="px-1.5 py-0.5 bg-exo-yellow/20 text-exo-yellow rounded"
+            >{cap}</span
+          >
+        {/each}
+        {#if filters.downloadedOnly}
+          <span class="px-1.5 py-0.5 bg-green-500/20 text-green-400 rounded"
+            >Downloaded</span
+          >
+        {/if}
+        {#if filters.sizeRange}
+          <span class="px-1.5 py-0.5 bg-exo-yellow/20 text-exo-yellow rounded">
+            {filters.sizeRange.min}GB - {filters.sizeRange.max}GB
+          </span>
+        {/if}
+        <button
+          type="button"
+          class="ml-auto text-white/40 hover:text-white/60"
+          onclick={clearFilters}
+        >
+          Clear all
+        </button>
+      </div>
+    {/if}
+  </div>
+
+  <!-- Info modal -->
+  {#if infoGroup}
+    <div
+      class="fixed inset-0 z-[60] bg-black/60"
+      transition:fade={{ duration: 150 }}
+      onclick={() => (infoGroup = null)}
+      role="presentation"
+    ></div>
+    <div
+      class="fixed z-[60] top-1/2 left-1/2 -translate-x-1/2 -translate-y-1/2 w-[min(80vw,400px)] bg-exo-dark-gray border border-exo-yellow/10 rounded-lg shadow-2xl p-4"
+      transition:fly={{ y: 10, duration: 200, easing: cubicOut }}
+      role="dialog"
+      aria-modal="true"
+    >
+      <div class="flex items-start justify-between mb-3">
+        <h3 class="font-mono text-lg text-white">{infoGroup.name}</h3>
+        <button
+          type="button"
+          class="p-1 rounded hover:bg-white/10 transition-colors text-white/50"
+          onclick={() => (infoGroup = null)}
+          title="Close model details"
+          aria-label="Close info dialog"
+        >
+          <svg class="w-4 h-4" viewBox="0 0 24 24" fill="currentColor">
+            <path
+              d="M19 6.41L17.59 5 12 10.59 6.41 5 5 6.41 10.59 12 5 17.59 6.41 19 12 13.41 17.59 19 19 17.59 13.41 12 19 6.41z"
+            />
+          </svg>
+        </button>
+      </div>
+      <div class="space-y-2 text-xs font-mono">
+        <div class="flex items-center gap-2">
+          <span class="text-white/40">Family:</span>
+          <span class="text-white/70">{infoGroup.family || "Unknown"}</span>
+        </div>
+        <div class="flex items-center gap-2">
+          <span class="text-white/40">Capabilities:</span>
+          <span class="text-white/70">{infoGroup.capabilities.join(", ")}</span>
+        </div>
+        <div class="flex items-center gap-2">
+          <span class="text-white/40">Variants:</span>
+          <span class="text-white/70">{infoGroup.variants.length}</span>
+        </div>
+        {#if infoGroup.variants.length > 0}
+          <div class="mt-3 pt-3 border-t border-exo-yellow/10">
+            <span class="text-white/40">Available quantizations:</span>
+            <div class="flex flex-wrap gap-1 mt-1">
+              {#each infoGroup.variants as variant}
+                <span
+                  class="px-1.5 py-0.5 bg-white/10 text-white/60 rounded text-[10px]"
+                >
+                  {variant.quantization || "default"} ({Math.round(
+                    (variant.storage_size_megabytes || 0) / 1024,
+                  )}GB)
+                </span>
+              {/each}
+            </div>
+          </div>
+        {/if}
+        {#if getGroupDownloadAvailability(infoGroup)?.nodeNames?.length}
+          {@const infoDownload = getGroupDownloadAvailability(infoGroup)}
+          {#if infoDownload}
+            <div class="mt-3 pt-3 border-t border-exo-yellow/10">
+              <div class="flex items-center gap-2 mb-1">
+                <svg
+                  class="w-3.5 h-3.5"
+                  viewBox="0 0 24 24"
+                  fill="none"
+                  stroke="currentColor"
+                  stroke-width="2"
+                  stroke-linecap="round"
+                  stroke-linejoin="round"
+                >
+                  <path
+                    class="text-white/40"
+                    d="M20 20a2 2 0 0 0 2-2V8a2 2 0 0 0-2-2h-7.9a2 2 0 0 1-1.69-.9L9.6 3.9A2 2 0 0 0 7.93 3H4a2 2 0 0 0-2 2v13a2 2 0 0 0 2 2Z"
+                  />
+                  <path class="text-green-400" d="m9 13 2 2 4-4" />
+                </svg>
+                <span class="text-white/40">Downloaded on:</span>
+              </div>
+              <div class="flex flex-wrap gap-1 mt-1">
+                {#each infoDownload.nodeNames as nodeName}
+                  <span
+                    class="px-1.5 py-0.5 bg-green-500/10 text-green-400/80 border border-green-500/20 rounded text-[10px]"
+                  >
+                    {nodeName}
+                  </span>
+                {/each}
+              </div>
+            </div>
+          {/if}
+        {/if}
+      </div>
+    </div>
+  {/if}
+{/if}

dashboard/src/lib/components/TokenHeatmap.svelte

@@ -0,0 +1,236 @@
+<script lang="ts">
+  import type { TokenData } from "$lib/stores/app.svelte";
+
+  interface Props {
+    tokens: TokenData[];
+    class?: string;
+    isGenerating?: boolean;
+    onRegenerateFrom?: (tokenIndex: number) => void;
+  }
+
+  let {
+    tokens,
+    class: className = "",
+    isGenerating = false,
+    onRegenerateFrom,
+  }: Props = $props();
+
+  // Tooltip state - track both token data and index
+  let hoveredTokenIndex = $state<number | null>(null);
+  let hoveredPosition = $state<{ x: number; y: number } | null>(null);
+  let isTooltipHovered = $state(false);
+  let hideTimeoutId: ReturnType<typeof setTimeout> | null = null;
+
+  // Derive the hovered token from the index (stable across re-renders)
+  const hoveredToken = $derived(
+    hoveredTokenIndex !== null && hoveredPosition && tokens[hoveredTokenIndex]
+      ? {
+          token: tokens[hoveredTokenIndex],
+          index: hoveredTokenIndex,
+          ...hoveredPosition,
+        }
+      : null,
+  );
+
+  /**
+   * Get confidence styling based on probability.
+   * Following Apple design principles: high confidence tokens blend in,
+   * only uncertainty draws attention.
+   */
+  function getConfidenceClass(probability: number): string {
+    if (probability > 0.8) return "text-inherit"; // Expected tokens - blend in
+    if (probability > 0.5) return "bg-gray-500/10 text-inherit"; // Slight hint
+    if (probability > 0.2) return "bg-amber-500/15 text-amber-200/90"; // Subtle warmth
+    return "bg-red-500/20 text-red-200/90"; // Draws attention
+  }
+
+  /**
+   * Get border/underline styling for uncertain tokens
+   */
+  function getBorderClass(probability: number): string {
+    if (probability > 0.8) return "border-transparent"; // No border for expected
+    if (probability > 0.5) return "border-gray-500/20";
+    if (probability > 0.2) return "border-amber-500/30";
+    return "border-red-500/40";
+  }
+
+  function clearHideTimeout() {
+    if (hideTimeoutId) {
+      clearTimeout(hideTimeoutId);
+      hideTimeoutId = null;
+    }
+  }
+
+  function handleMouseEnter(
+    event: MouseEvent,
+    token: TokenData,
+    index: number,
+  ) {
+    clearHideTimeout();
+    const rects = (event.target as HTMLElement).getClientRects();
+    let rect = rects[0];
+    for (let j = 0; j < rects.length; j++) {
+      if (event.clientY >= rects[j].top && event.clientY <= rects[j].bottom) {
+        rect = rects[j];
+        break;
+      }
+    }
+    hoveredTokenIndex = index;
+    hoveredPosition = {
+      x: rect.left + rect.width / 2,
+      y: rect.top - 10,
+    };
+  }
+
+  function handleMouseLeave() {
+    clearHideTimeout();
+    // Use longer delay during generation to account for re-renders
+    const delay = isGenerating ? 300 : 200;
+    hideTimeoutId = setTimeout(() => {
+      if (!isTooltipHovered) {
+        hoveredTokenIndex = null;
+        hoveredPosition = null;
+      }
+    }, delay);
+  }
+
+  function handleTooltipEnter() {
+    clearHideTimeout();
+    isTooltipHovered = true;
+  }
+
+  function handleTooltipLeave() {
+    isTooltipHovered = false;
+    hoveredTokenIndex = null;
+    hoveredPosition = null;
+  }
+
+  function handleRegenerate() {
+    if (hoveredToken && onRegenerateFrom) {
+      const indexToRegenerate = hoveredToken.index;
+      // Clear hover state immediately
+      hoveredTokenIndex = null;
+      hoveredPosition = null;
+      isTooltipHovered = false;
+      // Call regenerate
+      onRegenerateFrom(indexToRegenerate);
+    }
+  }
+
+  function formatProbability(prob: number): string {
+    return (prob * 100).toFixed(1) + "%";
+  }
+
+  function formatLogprob(logprob: number): string {
+    return logprob.toFixed(3);
+  }
+
+  function getProbabilityColor(probability: number): string {
+    if (probability > 0.8) return "text-gray-300";
+    if (probability > 0.5) return "text-gray-400";
+    if (probability > 0.2) return "text-amber-400";
+    return "text-red-400";
+  }
+</script>
+
+<div class="token-heatmap leading-relaxed {className}">
+  {#each tokens as tokenData, i (i)}
+    <span
+      role="button"
+      tabindex="0"
+      class="token-span inline rounded px-0.5 py-0.5 cursor-pointer transition-all duration-150 border {getConfidenceClass(
+        tokenData.probability,
+      )} {getBorderClass(tokenData.probability)} hover:opacity-80"
+      onmouseenter={(e) => handleMouseEnter(e, tokenData, i)}
+      onmouseleave={handleMouseLeave}>{tokenData.token}</span
+    >
+  {/each}
+</div>
+
+<!-- Tooltip -->
+{#if hoveredToken}
+  <div
+    class="fixed z-50 pb-2"
+    style="left: {hoveredToken.x}px; top: {hoveredToken.y}px; transform: translate(-50%, -100%);"
+    onmouseenter={handleTooltipEnter}
+    onmouseleave={handleTooltipLeave}
+  >
+    <div
+      class="bg-gray-900/95 backdrop-blur-sm border border-gray-700/50 rounded-xl shadow-xl p-3 text-sm min-w-48"
+    >
+      <!-- Token info -->
+      <div class="mb-2">
+        <span class="text-gray-500 text-xs">Token:</span>
+        <span class="text-white font-mono ml-1"
+          >"{hoveredToken.token.token}"</span
+        >
+        <span class="{getProbabilityColor(hoveredToken.token.probability)} ml-2"
+          >{formatProbability(hoveredToken.token.probability)}</span
+        >
+      </div>
+
+      <div class="text-gray-400 text-xs mb-1">
+        logprob: <span class="text-gray-300 font-mono"
+          >{formatLogprob(hoveredToken.token.logprob)}</span
+        >
+      </div>
+
+      <!-- Top alternatives -->
+      {#if hoveredToken.token.topLogprobs.length > 0}
+        <div class="border-t border-gray-700/50 mt-2 pt-2">
+          <div class="text-gray-500 text-xs mb-1">Alternatives:</div>
+          {#each hoveredToken.token.topLogprobs.slice(0, 5) as alt, idx (idx)}
+            {@const altProb = Math.exp(alt.logprob)}
+            <div class="flex justify-between items-center text-xs py-0.5">
+              <span class="text-gray-300 font-mono truncate max-w-24"
+                >"{alt.token}"</span
+              >
+              <span class="text-gray-400 ml-2"
+                >{formatProbability(altProb)}</span
+              >
+            </div>
+          {/each}
+        </div>
+      {/if}
+
+      <!-- Regenerate button -->
+      {#if onRegenerateFrom}
+        <button
+          onclick={handleRegenerate}
+          class="w-full mt-2 pt-2 border-t border-gray-700/50 flex items-center justify-center gap-1.5 text-xs text-gray-400 hover:text-white transition-colors cursor-pointer"
+        >
+          <svg
+            class="w-3 h-3"
+            fill="none"
+            viewBox="0 0 24 24"
+            stroke="currentColor"
+          >
+            <path
+              stroke-linecap="round"
+              stroke-linejoin="round"
+              stroke-width="2"
+              d="M4 4v5h.582m15.356 2A8.001 8.001 0 004.582 9m0 0H9m11 11v-5h-.581m0 0a8.003 8.003 0 01-15.357-2m15.357 2H15"
+            />
+          </svg>
+          Regenerate from here
+        </button>
+      {/if}
+    </div>
+    <!-- Arrow -->
+    <div class="absolute left-1/2 -translate-x-1/2 top-full">
+      <div class="border-8 border-transparent border-t-gray-900"></div>
+    </div>
+  </div>
+{/if}
+
+<style>
+  .token-heatmap {
+    word-wrap: break-word;
+    white-space: pre-wrap;
+  }
+
+  .token-span {
+    margin: 0;
+    border-width: 1px;
+  }
+</style>

dashboard/src/lib/components/TopologyGraph.svelte

@@ -6,6 +6,8 @@
     isTopologyMinimized,
     debugMode,
     nodeThunderboltBridge,
+    nodeRdmaCtl,
+    nodeIdentities,
     type NodeInfo,
   } from "$lib/stores/app.svelte";
 
@@ -31,6 +33,8 @@
   const data = $derived(topologyData());
   const debugEnabled = $derived(debugMode());
   const tbBridgeData = $derived(nodeThunderboltBridge());
+  const rdmaCtlData = $derived(nodeRdmaCtl());
+  const identitiesData = $derived(nodeIdentities());
 
   function getNodeLabel(nodeId: string): string {
     const node = data?.nodes?.[nodeId];
@@ -333,14 +337,27 @@
       if (edge.source === a) entry.aToB = true;
       else entry.bToA = true;
 
-      const ip = edge.sendBackIp || "?";
-      const ifaceInfo = getInterfaceLabel(edge.source, ip);
+      let ip: string;
+      let ifaceLabel: string;
+      let missingIface: boolean;
+
+      if (edge.sourceRdmaIface || edge.sinkRdmaIface) {
+        ip = "RDMA";
+        ifaceLabel = `${edge.sourceRdmaIface || "?"} \u2192 ${edge.sinkRdmaIface || "?"}`;
+        missingIface = false;
+      } else {
+        ip = edge.sendBackIp || "?";
+        const ifaceInfo = getInterfaceLabel(edge.source, ip);
+        ifaceLabel = ifaceInfo.label;
+        missingIface = ifaceInfo.missing;
+      }
+
       entry.connections.push({
         from: edge.source,
         to: edge.target,
         ip,
-        ifaceLabel: ifaceInfo.label,
-        missingIface: ifaceInfo.missing,
+        ifaceLabel,
+        missingIface,
       });
       pairMap.set(key, entry);
     });
@@ -1120,15 +1137,17 @@
           .text(` (${ramUsagePercent.toFixed(0)}%)`);
       }
 
-      // Debug mode: Show TB bridge status
+      // Debug mode: Show TB bridge and RDMA status
       if (debugEnabled) {
+        let debugLabelY =
+          nodeInfo.y +
+          iconBaseHeight / 2 +
+          (showFullLabels ? 32 : showCompactLabels ? 26 : 22);
+        const debugFontSize = showFullLabels ? 9 : 7;
+        const debugLineHeight = showFullLabels ? 11 : 9;
+
         const tbStatus = tbBridgeData[nodeInfo.id];
         if (tbStatus) {
-          const tbY =
-            nodeInfo.y +
-            iconBaseHeight / 2 +
-            (showFullLabels ? 32 : showCompactLabels ? 26 : 22);
-          const tbFontSize = showFullLabels ? 9 : 7;
           const tbColor = tbStatus.enabled
             ? "rgba(234,179,8,0.9)"
             : "rgba(100,100,100,0.7)";
@@ -1136,12 +1155,46 @@
           nodeG
             .append("text")
             .attr("x", nodeInfo.x)
-            .attr("y", tbY)
+            .attr("y", debugLabelY)
             .attr("text-anchor", "middle")
             .attr("fill", tbColor)
-            .attr("font-size", tbFontSize)
+            .attr("font-size", debugFontSize)
             .attr("font-family", "SF Mono, Monaco, monospace")
             .text(tbText);
+          debugLabelY += debugLineHeight;
+        }
+
+        const rdmaStatus = rdmaCtlData[nodeInfo.id];
+        if (rdmaStatus !== undefined) {
+          const rdmaColor = rdmaStatus.enabled
+            ? "rgba(74,222,128,0.9)"
+            : "rgba(100,100,100,0.7)";
+          const rdmaText = rdmaStatus.enabled ? "RDMA:ON" : "RDMA:OFF";
+          nodeG
+            .append("text")
+            .attr("x", nodeInfo.x)
+            .attr("y", debugLabelY)
+            .attr("text-anchor", "middle")
+            .attr("fill", rdmaColor)
+            .attr("font-size", debugFontSize)
+            .attr("font-family", "SF Mono, Monaco, monospace")
+            .text(rdmaText);
+          debugLabelY += debugLineHeight;
+        }
+
+        const identity = identitiesData[nodeInfo.id];
+        if (identity?.osVersion) {
+          nodeG
+            .append("text")
+            .attr("x", nodeInfo.x)
+            .attr("y", debugLabelY)
+            .attr("text-anchor", "middle")
+            .attr("fill", "rgba(179,179,179,0.7)")
+            .attr("font-size", debugFontSize)
+            .attr("font-family", "SF Mono, Monaco, monospace")
+            .text(
+              `macOS ${identity.osVersion}${identity.osBuildVersion ? ` (${identity.osBuildVersion})` : ""}`,
+            );
         }
       }
     });

dashboard/src/lib/components/index.ts

@@ -6,3 +6,9 @@ export { default as ChatSidebar } from "./ChatSidebar.svelte";
 export { default as ModelCard } from "./ModelCard.svelte";
 export { default as MarkdownContent } from "./MarkdownContent.svelte";
 export { default as ImageParamsPanel } from "./ImageParamsPanel.svelte";
+export { default as FamilyLogos } from "./FamilyLogos.svelte";
+export { default as FamilySidebar } from "./FamilySidebar.svelte";
+export { default as HuggingFaceResultItem } from "./HuggingFaceResultItem.svelte";
+export { default as ModelFilterPopover } from "./ModelFilterPopover.svelte";
+export { default as ModelPickerGroup } from "./ModelPickerGroup.svelte";
+export { default as ModelPickerModal } from "./ModelPickerModal.svelte";

dashboard/src/lib/stores/app.svelte.ts

@@ -49,6 +49,7 @@ export interface NodeInfo {
   };
   last_macmon_update: number;
   friendly_name?: string;
+  os_version?: string;
 }
 
 export interface TopologyEdge {
@@ -56,6 +57,8 @@ export interface TopologyEdge {
   target: string;
   sendBackIp?: string;
   sendBackInterface?: string;
+  sourceRdmaIface?: string;
+  sinkRdmaIface?: string;
 }
 
 export interface TopologyData {
@@ -76,6 +79,8 @@ interface RawNodeIdentity {
   modelId?: string;
   chipId?: string;
   friendlyName?: string;
+  osVersion?: string;
+  osBuildVersion?: string;
 }
 
 interface RawMemoryUsage {
@@ -225,6 +230,19 @@ interface RawStateResponse {
   nodeMemory?: Record<string, RawMemoryUsage>;
   nodeSystem?: Record<string, RawSystemPerformanceProfile>;
   nodeNetwork?: Record<string, RawNodeNetworkInfo>;
+  // Thunderbolt identifiers per node
+  nodeThunderbolt?: Record<
+    string,
+    {
+      interfaces: Array<{
+        rdmaInterface: string;
+        domainUuid: string;
+        linkSpeed: string;
+      }>;
+    }
+  >;
+  // RDMA ctl status per node
+  nodeRdmaCtl?: Record<string, { enabled: boolean }>;
   // Thunderbolt bridge status per node
   nodeThunderboltBridge?: Record<
     string,
@@ -242,6 +260,19 @@ export interface MessageAttachment {
   mimeType?: string;
 }
 
+export interface TopLogprob {
+  token: string;
+  logprob: number;
+  bytes: number[] | null;
+}
+
+export interface TokenData {
+  token: string;
+  logprob: number;
+  probability: number;
+  topLogprobs: TopLogprob[];
+}
+
 export interface Message {
   id: string;
   role: "user" | "assistant" | "system";
@@ -253,6 +284,7 @@ export interface Message {
   tps?: number; // Tokens per second (for assistant messages)
   requestType?: "chat" | "image-generation" | "image-editing";
   sourceImageDataUrl?: string; // For image editing regeneration
+  tokens?: TokenData[];
 }
 
 export interface Conversation {
@@ -264,6 +296,7 @@ export interface Conversation {
   modelId: string | null;
   sharding: string | null;
   instanceType: string | null;
+  enableThinking: boolean | null;
 }
 
 const STORAGE_KEY = "exo-conversations";
@@ -272,7 +305,14 @@ const IMAGE_PARAMS_STORAGE_KEY = "exo-image-generation-params";
 // Image generation params interface matching backend API
 export interface ImageGenerationParams {
   // Basic params
-  size: "512x512" | "768x768" | "1024x1024" | "1024x768" | "768x1024";
+  size:
+    | "512x512"
+    | "768x768"
+    | "1024x1024"
+    | "1024x768"
+    | "768x1024"
+    | "1024x1365"
+    | "1365x1024";
   quality: "low" | "medium" | "high";
   outputFormat: "png" | "jpeg";
   numImages: number;
@@ -284,6 +324,7 @@ export interface ImageGenerationParams {
   numInferenceSteps: number | null;
   guidance: number | null;
   negativePrompt: string | null;
+  numSyncSteps: number | null;
   // Edit mode params
   inputFidelity: "low" | "high";
 }
@@ -305,6 +346,7 @@ const DEFAULT_IMAGE_PARAMS: ImageGenerationParams = {
   numInferenceSteps: null,
   guidance: null,
   negativePrompt: null,
+  numSyncSteps: null,
   inputFidelity: "low",
 };
 
@@ -402,6 +444,7 @@ function transformTopology(
       },
       last_macmon_update: Date.now() / 1000,
       friendly_name: identity?.friendlyName,
+      os_version: identity?.osVersion,
     };
   }
 
@@ -414,6 +457,8 @@ function transformTopology(
         if (!Array.isArray(edgeList)) continue;
         for (const edge of edgeList) {
           let sendBackIp: string | undefined;
+          let sourceRdmaIface: string | undefined;
+          let sinkRdmaIface: string | undefined;
           if (edge && typeof edge === "object" && "sinkMultiaddr" in edge) {
             const multiaddr = edge.sinkMultiaddr;
             if (multiaddr) {
@@ -421,10 +466,23 @@ function transformTopology(
                 multiaddr.ip_address ||
                 extractIpFromMultiaddr(multiaddr.address);
             }
+          } else if (
+            edge &&
+            typeof edge === "object" &&
+            "sourceRdmaIface" in edge
+          ) {
+            sourceRdmaIface = edge.sourceRdmaIface;
+            sinkRdmaIface = edge.sinkRdmaIface;
           }
 
           if (nodes[source] && nodes[sink] && source !== sink) {
-            edges.push({ source, target: sink, sendBackIp });
+            edges.push({
+              source,
+              target: sink,
+              sendBackIp,
+              sourceRdmaIface,
+              sinkRdmaIface,
+            });
           }
         }
       }
@@ -467,12 +525,32 @@ class AppStore {
   instances = $state<Record<string, unknown>>({});
   runners = $state<Record<string, unknown>>({});
   downloads = $state<Record<string, unknown[]>>({});
+  nodeDisk = $state<
+    Record<
+      string,
+      { total: { inBytes: number }; available: { inBytes: number } }
+    >
+  >({});
   placementPreviews = $state<PlacementPreview[]>([]);
   selectedPreviewModelId = $state<string | null>(null);
   isLoadingPreviews = $state(false);
   previewNodeFilter = $state<Set<string>>(new Set());
   lastUpdate = $state<number | null>(null);
+  nodeIdentities = $state<Record<string, RawNodeIdentity>>({});
   thunderboltBridgeCycles = $state<string[][]>([]);
+  nodeThunderbolt = $state<
+    Record<
+      string,
+      {
+        interfaces: Array<{
+          rdmaInterface: string;
+          domainUuid: string;
+          linkSpeed: string;
+        }>;
+      }
+    >
+  >({});
+  nodeRdmaCtl = $state<Record<string, { enabled: boolean }>>({});
   nodeThunderboltBridge = $state<
     Record<
       string,
@@ -528,6 +606,7 @@ class AppStore {
           modelId: conversation.modelId ?? null,
           sharding: conversation.sharding ?? null,
           instanceType: conversation.instanceType ?? null,
+          enableThinking: conversation.enableThinking ?? null,
         }));
       }
     } catch (error) {
@@ -540,7 +619,18 @@ class AppStore {
    */
   private saveConversationsToStorage() {
     try {
-      localStorage.setItem(STORAGE_KEY, JSON.stringify(this.conversations));
+      // Strip tokens from messages before saving to avoid bloating localStorage
+      const stripped = this.conversations.map((conv) => ({
+        ...conv,
+        messages: conv.messages.map((msg) => {
+          if (msg.tokens) {
+            const { tokens: _, ...rest } = msg;
+            return rest;
+          }
+          return msg;
+        }),
+      }));
+      localStorage.setItem(STORAGE_KEY, JSON.stringify(stripped));
     } catch (error) {
       console.error("Failed to save conversations:", error);
     }
@@ -706,6 +796,7 @@ class AppStore {
       modelId: derivedModelId,
       sharding: derivedSharding,
       instanceType: derivedInstanceType,
+      enableThinking: null,
     };
 
     this.conversations.unshift(conversation);
@@ -731,6 +822,7 @@ class AppStore {
     this.hasStartedChat = true;
     this.isTopologyMinimized = true;
     this.isSidebarOpen = true; // Auto-open sidebar when chatting
+    this.thinkingEnabled = conversation.enableThinking ?? true;
     this.refreshConversationModelFromInstances();
 
     return true;
@@ -1172,6 +1264,15 @@ class AppStore {
       if (data.downloads) {
         this.downloads = data.downloads;
       }
+      if (data.nodeDisk) {
+        this.nodeDisk = data.nodeDisk;
+      }
+      // Node identities (for OS version mismatch detection)
+      this.nodeIdentities = data.nodeIdentities ?? {};
+      // Thunderbolt identifiers per node
+      this.nodeThunderbolt = data.nodeThunderbolt ?? {};
+      // RDMA ctl status per node
+      this.nodeRdmaCtl = data.nodeRdmaCtl ?? {};
       // Thunderbolt bridge cycles
       this.thunderboltBridgeCycles = data.thunderboltBridgeCycles ?? [];
       // Thunderbolt bridge status per node
@@ -1445,6 +1546,213 @@ class AppStore {
     }
   }
 
+  /**
+   * Regenerate response from a specific token index.
+   * Truncates the assistant message at the given token and re-generates from there.
+   */
+  async regenerateFromToken(
+    messageId: string,
+    tokenIndex: number,
+  ): Promise<void> {
+    if (this.isLoading) return;
+
+    const targetConversationId = this.activeConversationId;
+    if (!targetConversationId) return;
+
+    const msgIndex = this.messages.findIndex((m) => m.id === messageId);
+    if (msgIndex === -1) return;
+
+    const msg = this.messages[msgIndex];
+    if (
+      msg.role !== "assistant" ||
+      !msg.tokens ||
+      tokenIndex >= msg.tokens.length
+    )
+      return;
+
+    // Keep tokens up to (not including) the specified index
+    const tokensToKeep = msg.tokens.slice(0, tokenIndex);
+    const prefixText = tokensToKeep.map((t) => t.token).join("");
+
+    // Remove all messages after this assistant message
+    this.messages = this.messages.slice(0, msgIndex + 1);
+
+    // Update the message to show the prefix
+    this.messages[msgIndex].content = prefixText;
+    this.messages[msgIndex].tokens = tokensToKeep;
+    this.updateActiveConversation();
+
+    // Set up for continuation - modify the existing message in place
+    this.isLoading = true;
+    this.currentResponse = prefixText;
+    this.ttftMs = null;
+    this.tps = null;
+    this.totalTokens = tokensToKeep.length;
+
+    try {
+      // Build messages for API - include the partial assistant message
+      const systemPrompt = {
+        role: "system" as const,
+        content:
+          "You are a helpful AI assistant. Respond directly and concisely. Do not show your reasoning or thought process.",
+      };
+
+      const apiMessages = [
+        systemPrompt,
+        ...this.messages.map((m) => {
+          let msgContent = m.content;
+          if (m.attachments) {
+            for (const attachment of m.attachments) {
+              if (attachment.type === "text" && attachment.content) {
+                msgContent += `\n\n[File: ${attachment.name}]\n\`\`\`\n${attachment.content}\n\`\`\``;
+              }
+            }
+          }
+          return { role: m.role, content: msgContent };
+        }),
+      ];
+
+      const modelToUse = this.getModelForRequest();
+      if (!modelToUse) {
+        throw new Error("No model available");
+      }
+
+      const requestStartTime = performance.now();
+      let firstTokenTime: number | null = null;
+      let tokenCount = tokensToKeep.length;
+
+      const response = await fetch("/v1/chat/completions", {
+        method: "POST",
+        headers: { "Content-Type": "application/json" },
+        body: JSON.stringify({
+          model: modelToUse,
+          messages: apiMessages,
+          stream: true,
+          logprobs: true,
+          top_logprobs: 5,
+        }),
+      });
+
+      if (!response.ok) {
+        const errorText = await response.text();
+        throw new Error(`API error: ${response.status} - ${errorText}`);
+      }
+
+      const reader = response.body?.getReader();
+      if (!reader) throw new Error("No response body");
+
+      let fullContent = prefixText;
+      const collectedTokens: TokenData[] = [...tokensToKeep];
+
+      interface ChatCompletionChunk {
+        choices?: Array<{
+          delta?: { content?: string };
+          logprobs?: {
+            content?: Array<{
+              token: string;
+              logprob: number;
+              top_logprobs?: Array<{
+                token: string;
+                logprob: number;
+                bytes: number[] | null;
+              }>;
+            }>;
+          };
+        }>;
+      }
+
+      await this.parseSSEStream<ChatCompletionChunk>(
+        reader,
+        targetConversationId,
+        (parsed) => {
+          const choice = parsed.choices?.[0];
+          const delta = choice?.delta?.content;
+
+          // Collect logprobs data
+          const logprobsContent = choice?.logprobs?.content;
+          if (logprobsContent) {
+            for (const item of logprobsContent) {
+              collectedTokens.push({
+                token: item.token,
+                logprob: item.logprob,
+                probability: Math.exp(item.logprob),
+                topLogprobs: (item.top_logprobs || []).map((t) => ({
+                  token: t.token,
+                  logprob: t.logprob,
+                  bytes: t.bytes,
+                })),
+              });
+            }
+          }
+
+          if (delta) {
+            if (firstTokenTime === null) {
+              firstTokenTime = performance.now();
+              this.ttftMs = firstTokenTime - requestStartTime;
+            }
+
+            tokenCount += 1;
+            this.totalTokens = tokenCount;
+
+            if (firstTokenTime !== null && tokenCount > tokensToKeep.length) {
+              const elapsed = performance.now() - firstTokenTime;
+              this.tps = ((tokenCount - tokensToKeep.length) / elapsed) * 1000;
+            }
+
+            fullContent += delta;
+            const { displayContent, thinkingContent } =
+              this.stripThinkingTags(fullContent);
+
+            if (this.activeConversationId === targetConversationId) {
+              this.currentResponse = displayContent;
+            }
+
+            // Update existing message in place
+            this.updateConversationMessage(
+              targetConversationId,
+              messageId,
+              (m) => {
+                m.content = displayContent;
+                m.thinking = thinkingContent || undefined;
+                m.tokens = [...collectedTokens];
+              },
+            );
+            this.syncActiveMessagesIfNeeded(targetConversationId);
+            this.persistConversation(targetConversationId);
+          }
+        },
+      );
+
+      // Final update
+      if (this.conversationExists(targetConversationId)) {
+        const { displayContent, thinkingContent } =
+          this.stripThinkingTags(fullContent);
+        this.updateConversationMessage(targetConversationId, messageId, (m) => {
+          m.content = displayContent;
+          m.thinking = thinkingContent || undefined;
+          m.tokens = [...collectedTokens];
+          if (this.ttftMs !== null) m.ttftMs = this.ttftMs;
+          if (this.tps !== null) m.tps = this.tps;
+        });
+        this.syncActiveMessagesIfNeeded(targetConversationId);
+        this.persistConversation(targetConversationId);
+      }
+    } catch (error) {
+      console.error("Error regenerating from token:", error);
+      if (this.conversationExists(targetConversationId)) {
+        this.updateConversationMessage(targetConversationId, messageId, (m) => {
+          m.content = `${prefixText}\n\nError: ${error instanceof Error ? error.message : "Unknown error"}`;
+        });
+        this.syncActiveMessagesIfNeeded(targetConversationId);
+        this.persistConversation(targetConversationId);
+      }
+    } finally {
+      this.isLoading = false;
+      this.currentResponse = "";
+      this.saveConversationsToStorage();
+    }
+  }
+
   /**
    * Helper method to regenerate a chat completion response
    */
@@ -1513,6 +1821,8 @@ class AppStore {
           model: modelToUse,
           messages: apiMessages,
           stream: true,
+          logprobs: true,
+          top_logprobs: 5,
         }),
       });
 
@@ -1527,16 +1837,49 @@ class AppStore {
       }
 
       let streamedContent = "";
+      const collectedTokens: TokenData[] = [];
 
       interface ChatCompletionChunk {
-        choices?: Array<{ delta?: { content?: string } }>;
+        choices?: Array<{
+          delta?: { content?: string };
+          logprobs?: {
+            content?: Array<{
+              token: string;
+              logprob: number;
+              top_logprobs?: Array<{
+                token: string;
+                logprob: number;
+                bytes: number[] | null;
+              }>;
+            }>;
+          };
+        }>;
       }
 
       await this.parseSSEStream<ChatCompletionChunk>(
         reader,
         targetConversationId,
         (parsed) => {
-          const delta = parsed.choices?.[0]?.delta?.content;
+          const choice = parsed.choices?.[0];
+          const delta = choice?.delta?.content;
+
+          // Collect logprobs data
+          const logprobsContent = choice?.logprobs?.content;
+          if (logprobsContent) {
+            for (const item of logprobsContent) {
+              collectedTokens.push({
+                token: item.token,
+                logprob: item.logprob,
+                probability: Math.exp(item.logprob),
+                topLogprobs: (item.top_logprobs || []).map((t) => ({
+                  token: t.token,
+                  logprob: t.logprob,
+                  bytes: t.bytes,
+                })),
+              });
+            }
+          }
+
           if (delta) {
             streamedContent += delta;
             const { displayContent, thinkingContent } =
@@ -1554,6 +1897,7 @@ class AppStore {
               (msg) => {
                 msg.content = displayContent;
                 msg.thinking = thinkingContent || undefined;
+                msg.tokens = [...collectedTokens];
               },
             );
             this.syncActiveMessagesIfNeeded(targetConversationId);
@@ -1572,6 +1916,7 @@ class AppStore {
           (msg) => {
             msg.content = displayContent;
             msg.thinking = thinkingContent || undefined;
+            msg.tokens = [...collectedTokens];
           },
         );
         this.syncActiveMessagesIfNeeded(targetConversationId);
@@ -1591,6 +1936,11 @@ class AppStore {
     }
   }
 
+  /**
+   * Whether thinking is enabled for the current conversation
+   */
+  thinkingEnabled = $state(true);
+
   /**
    * Selected model for chat (can be set by the UI)
    */
@@ -1769,6 +2119,7 @@ class AppStore {
       textContent?: string;
       preview?: string;
     }[],
+    enableThinking?: boolean | null,
   ): Promise<void> {
     if ((!content.trim() && (!files || files.length === 0)) || this.isLoading)
       return;
@@ -1914,6 +2265,11 @@ class AppStore {
           messages: apiMessages,
           temperature: 0.7,
           stream: true,
+          logprobs: true,
+          top_logprobs: 5,
+          ...(enableThinking != null && {
+            enable_thinking: enableThinking,
+          }),
         }),
       });
 
@@ -1930,14 +2286,48 @@ class AppStore {
       let streamedContent = "";
 
       interface ChatCompletionChunk {
-        choices?: Array<{ delta?: { content?: string } }>;
+        choices?: Array<{
+          delta?: { content?: string };
+          logprobs?: {
+            content?: Array<{
+              token: string;
+              logprob: number;
+              top_logprobs?: Array<{
+                token: string;
+                logprob: number;
+                bytes: number[] | null;
+              }>;
+            }>;
+          };
+        }>;
       }
 
+      const collectedTokens: TokenData[] = [];
+
       await this.parseSSEStream<ChatCompletionChunk>(
         reader,
         targetConversationId,
         (parsed) => {
-          const tokenContent = parsed.choices?.[0]?.delta?.content;
+          const choice = parsed.choices?.[0];
+          const tokenContent = choice?.delta?.content;
+
+          // Collect logprobs data
+          const logprobsContent = choice?.logprobs?.content;
+          if (logprobsContent) {
+            for (const item of logprobsContent) {
+              collectedTokens.push({
+                token: item.token,
+                logprob: item.logprob,
+                probability: Math.exp(item.logprob),
+                topLogprobs: (item.top_logprobs || []).map((t) => ({
+                  token: t.token,
+                  logprob: t.logprob,
+                  bytes: t.bytes,
+                })),
+              });
+            }
+          }
+
           if (tokenContent) {
             // Track first token for TTFT
             if (firstTokenTime === null) {
@@ -1973,6 +2363,7 @@ class AppStore {
               (msg) => {
                 msg.content = displayContent;
                 msg.thinking = thinkingContent || undefined;
+                msg.tokens = [...collectedTokens];
               },
             );
             this.syncActiveMessagesIfNeeded(targetConversationId);
@@ -1997,6 +2388,7 @@ class AppStore {
           (msg) => {
             msg.content = displayContent;
             msg.thinking = thinkingContent || undefined;
+            msg.tokens = [...collectedTokens];
             // Store performance metrics on the message
             if (this.ttftMs !== null) {
               msg.ttftMs = this.ttftMs;
@@ -2089,7 +2481,9 @@ class AppStore {
         params.seed !== null ||
         params.numInferenceSteps !== null ||
         params.guidance !== null ||
-        (params.negativePrompt !== null && params.negativePrompt.trim() !== "");
+        (params.negativePrompt !== null &&
+          params.negativePrompt.trim() !== "") ||
+        params.numSyncSteps !== null;
 
       const requestBody: Record<string, unknown> = {
         model,
@@ -2114,6 +2508,9 @@ class AppStore {
             params.negativePrompt.trim() !== "" && {
               negative_prompt: params.negativePrompt,
             }),
+          ...(params.numSyncSteps !== null && {
+            num_sync_steps: params.numSyncSteps,
+          }),
         };
       }
 
@@ -2363,29 +2760,19 @@ class AppStore {
       formData.append("input_fidelity", params.inputFidelity);
 
       // Advanced params
-      if (params.seed !== null) {
-        formData.append(
-          "advanced_params",
-          JSON.stringify({
-            seed: params.seed,
-            ...(params.numInferenceSteps !== null && {
-              num_inference_steps: params.numInferenceSteps,
-            }),
-            ...(params.guidance !== null && { guidance: params.guidance }),
-            ...(params.negativePrompt !== null &&
-              params.negativePrompt.trim() !== "" && {
-                negative_prompt: params.negativePrompt,
-              }),
-          }),
-        );
-      } else if (
+      const hasAdvancedParams =
+        params.seed !== null ||
         params.numInferenceSteps !== null ||
         params.guidance !== null ||
-        (params.negativePrompt !== null && params.negativePrompt.trim() !== "")
-      ) {
+        (params.negativePrompt !== null &&
+          params.negativePrompt.trim() !== "") ||
+        params.numSyncSteps !== null;
+
+      if (hasAdvancedParams) {
         formData.append(
           "advanced_params",
           JSON.stringify({
+            ...(params.seed !== null && { seed: params.seed }),
             ...(params.numInferenceSteps !== null && {
               num_inference_steps: params.numInferenceSteps,
             }),
@@ -2394,6 +2781,9 @@ class AppStore {
               params.negativePrompt.trim() !== "" && {
                 negative_prompt: params.negativePrompt,
               }),
+            ...(params.numSyncSteps !== null && {
+              num_sync_steps: params.numSyncSteps,
+            }),
           }),
         );
       }
@@ -2538,6 +2928,18 @@ class AppStore {
     );
   }
 
+  /**
+   * Update the thinking preference for the active conversation
+   */
+  setConversationThinking(enabled: boolean) {
+    this.thinkingEnabled = enabled;
+    const conv = this.getActiveConversation();
+    if (conv) {
+      conv.enableThinking = enabled;
+      this.saveConversationsToStorage();
+    }
+  }
+
   /**
    * Start a download on a specific node
    */
@@ -2644,12 +3046,14 @@ export const topologyData = () => appStore.topologyData;
 export const instances = () => appStore.instances;
 export const runners = () => appStore.runners;
 export const downloads = () => appStore.downloads;
+export const nodeDisk = () => appStore.nodeDisk;
 export const placementPreviews = () => appStore.placementPreviews;
 export const selectedPreviewModelId = () => appStore.selectedPreviewModelId;
 export const isLoadingPreviews = () => appStore.isLoadingPreviews;
 export const lastUpdate = () => appStore.lastUpdate;
 export const isTopologyMinimized = () => appStore.isTopologyMinimized;
 export const selectedChatModel = () => appStore.selectedChatModel;
+export const thinkingEnabled = () => appStore.thinkingEnabled;
 export const debugMode = () => appStore.getDebugMode();
 export const topologyOnlyMode = () => appStore.getTopologyOnlyMode();
 export const chatSidebarVisible = () => appStore.getChatSidebarVisible();
@@ -2665,7 +3069,8 @@ export const sendMessage = (
     textContent?: string;
     preview?: string;
   }[],
-) => appStore.sendMessage(content, files);
+  enableThinking?: boolean | null,
+) => appStore.sendMessage(content, files, enableThinking);
 export const generateImage = (prompt: string, modelId?: string) =>
   appStore.generateImage(prompt, modelId);
 export const editImage = (
@@ -2693,6 +3098,8 @@ export const editMessage = (messageId: string, newContent: string) =>
 export const editAndRegenerate = (messageId: string, newContent: string) =>
   appStore.editAndRegenerate(messageId, newContent);
 export const regenerateLastResponse = () => appStore.regenerateLastResponse();
+export const regenerateFromToken = (messageId: string, tokenIndex: number) =>
+  appStore.regenerateFromToken(messageId, tokenIndex);
 
 // Conversation actions
 export const conversations = () => appStore.conversations;
@@ -2706,6 +3113,8 @@ export const deleteAllConversations = () => appStore.deleteAllConversations();
 export const renameConversation = (id: string, name: string) =>
   appStore.renameConversation(id, name);
 export const getActiveConversation = () => appStore.getActiveConversation();
+export const setConversationThinking = (enabled: boolean) =>
+  appStore.setConversationThinking(enabled);
 
 // Sidebar actions
 export const isSidebarOpen = () => appStore.isSidebarOpen;
@@ -2722,7 +3131,12 @@ export const setChatSidebarVisible = (visible: boolean) =>
   appStore.setChatSidebarVisible(visible);
 export const refreshState = () => appStore.fetchState();
 
-// Thunderbolt bridge status
+// Node identities (for OS version mismatch detection)
+export const nodeIdentities = () => appStore.nodeIdentities;
+
+// Thunderbolt & RDMA status
+export const nodeThunderbolt = () => appStore.nodeThunderbolt;
+export const nodeRdmaCtl = () => appStore.nodeRdmaCtl;
 export const thunderboltBridgeCycles = () => appStore.thunderboltBridgeCycles;
 export const nodeThunderboltBridge = () => appStore.nodeThunderboltBridge;
 

dashboard/src/lib/stores/favorites.svelte.ts

@@ -0,0 +1,97 @@
+/**
+ * FavoritesStore - Manages favorite models with localStorage persistence
+ */
+
+import { browser } from "$app/environment";
+
+const FAVORITES_KEY = "exo-favorite-models";
+
+class FavoritesStore {
+  favorites = $state<Set<string>>(new Set());
+
+  constructor() {
+    if (browser) {
+      this.loadFromStorage();
+    }
+  }
+
+  private loadFromStorage() {
+    try {
+      const stored = localStorage.getItem(FAVORITES_KEY);
+      if (stored) {
+        const parsed = JSON.parse(stored) as string[];
+        this.favorites = new Set(parsed);
+      }
+    } catch (error) {
+      console.error("Failed to load favorites:", error);
+    }
+  }
+
+  private saveToStorage() {
+    try {
+      const array = Array.from(this.favorites);
+      localStorage.setItem(FAVORITES_KEY, JSON.stringify(array));
+    } catch (error) {
+      console.error("Failed to save favorites:", error);
+    }
+  }
+
+  add(baseModelId: string) {
+    const next = new Set(this.favorites);
+    next.add(baseModelId);
+    this.favorites = next;
+    this.saveToStorage();
+  }
+
+  remove(baseModelId: string) {
+    const next = new Set(this.favorites);
+    next.delete(baseModelId);
+    this.favorites = next;
+    this.saveToStorage();
+  }
+
+  toggle(baseModelId: string) {
+    if (this.favorites.has(baseModelId)) {
+      this.remove(baseModelId);
+    } else {
+      this.add(baseModelId);
+    }
+  }
+
+  isFavorite(baseModelId: string): boolean {
+    return this.favorites.has(baseModelId);
+  }
+
+  getAll(): string[] {
+    return Array.from(this.favorites);
+  }
+
+  getSet(): Set<string> {
+    return new Set(this.favorites);
+  }
+
+  hasAny(): boolean {
+    return this.favorites.size > 0;
+  }
+
+  clearAll() {
+    this.favorites = new Set();
+    this.saveToStorage();
+  }
+}
+
+export const favoritesStore = new FavoritesStore();
+
+export const favorites = () => favoritesStore.favorites;
+export const hasFavorites = () => favoritesStore.hasAny();
+export const isFavorite = (baseModelId: string) =>
+  favoritesStore.isFavorite(baseModelId);
+export const toggleFavorite = (baseModelId: string) =>
+  favoritesStore.toggle(baseModelId);
+export const addFavorite = (baseModelId: string) =>
+  favoritesStore.add(baseModelId);
+export const removeFavorite = (baseModelId: string) =>
+  favoritesStore.remove(baseModelId);
+export const getFavorites = () => favoritesStore.getAll();
+export const getFavoritesSet = () => favoritesStore.getSet();
+export const clearFavorites = () => favoritesStore.clearAll();

dashboard/src/lib/stores/recents.svelte.ts

@@ -0,0 +1,75 @@
+/**
+ * RecentsStore - Manages recently launched models with localStorage persistence
+ */
+
+import { browser } from "$app/environment";
+
+const RECENTS_KEY = "exo-recent-models";
+const MAX_RECENT_MODELS = 20;
+
+interface RecentEntry {
+  modelId: string;
+  launchedAt: number;
+}
+
+class RecentsStore {
+  recents = $state<RecentEntry[]>([]);
+
+  constructor() {
+    if (browser) {
+      this.loadFromStorage();
+    }
+  }
+
+  private loadFromStorage() {
+    try {
+      const stored = localStorage.getItem(RECENTS_KEY);
+      if (stored) {
+        const parsed = JSON.parse(stored) as RecentEntry[];
+        this.recents = parsed;
+      }
+    } catch (error) {
+      console.error("Failed to load recent models:", error);
+    }
+  }
+
+  private saveToStorage() {
+    try {
+      localStorage.setItem(RECENTS_KEY, JSON.stringify(this.recents));
+    } catch (error) {
+      console.error("Failed to save recent models:", error);
+    }
+  }
+
+  recordLaunch(modelId: string) {
+    // Remove existing entry for this model (if any) to move it to top
+    const filtered = this.recents.filter((r) => r.modelId !== modelId);
+    // Prepend new entry
+    const next = [{ modelId, launchedAt: Date.now() }, ...filtered];
+    // Cap at max
+    this.recents = next.slice(0, MAX_RECENT_MODELS);
+    this.saveToStorage();
+  }
+
+  getRecentModelIds(): string[] {
+    return this.recents.map((r) => r.modelId);
+  }
+
+  hasAny(): boolean {
+    return this.recents.length > 0;
+  }
+
+  clearAll() {
+    this.recents = [];
+    this.saveToStorage();
+  }
+}
+
+export const recentsStore = new RecentsStore();
+
+export const hasRecents = () => recentsStore.hasAny();
+export const getRecentModelIds = () => recentsStore.getRecentModelIds();
+export const getRecentEntries = () => recentsStore.recents;
+export const recordRecentLaunch = (modelId: string) =>
+  recentsStore.recordLaunch(modelId);
+export const clearRecents = () => recentsStore.clearAll();

dashboard/src/lib/utils/downloads.ts

@@ -0,0 +1,152 @@
+/**
+ * Shared utilities for parsing and querying download state.
+ *
+ * The download state from `/state` is shaped as:
+ *   Record<NodeId, Array<TaggedDownloadEntry>>
+ *
+ * Each entry is a tagged union object like:
+ *   { "DownloadCompleted": { shard_metadata: { "PipelineShardMetadata": { model_card: { model_id: "..." }, ... } }, ... } }
+ */
+
+/** Unwrap one level of tagged-union envelope, returning [tag, payload]. */
+function unwrapTagged(
+  obj: Record<string, unknown>,
+): [string, Record<string, unknown>] | null {
+  const keys = Object.keys(obj);
+  if (keys.length !== 1) return null;
+  const tag = keys[0];
+  const payload = obj[tag];
+  if (!payload || typeof payload !== "object") return null;
+  return [tag, payload as Record<string, unknown>];
+}
+
+/** Extract the model ID string from a download entry's nested shard_metadata. */
+export function extractModelIdFromDownload(
+  downloadPayload: Record<string, unknown>,
+): string | null {
+  const shardMetadata =
+    downloadPayload.shard_metadata ?? downloadPayload.shardMetadata;
+  if (!shardMetadata || typeof shardMetadata !== "object") return null;
+
+  const unwrapped = unwrapTagged(shardMetadata as Record<string, unknown>);
+  if (!unwrapped) return null;
+  const [, shardData] = unwrapped;
+
+  const modelMeta = shardData.model_card ?? shardData.modelCard;
+  if (!modelMeta || typeof modelMeta !== "object") return null;
+
+  const meta = modelMeta as Record<string, unknown>;
+  return (meta.model_id as string) ?? (meta.modelId as string) ?? null;
+}
+
+/** Extract the shard_metadata object from a download entry payload. */
+export function extractShardMetadata(
+  downloadPayload: Record<string, unknown>,
+): Record<string, unknown> | null {
+  const shardMetadata =
+    downloadPayload.shard_metadata ?? downloadPayload.shardMetadata;
+  if (!shardMetadata || typeof shardMetadata !== "object") return null;
+  return shardMetadata as Record<string, unknown>;
+}
+
+/** Get the download tag (DownloadCompleted, DownloadOngoing, etc.) from a wrapped entry. */
+export function getDownloadTag(
+  entry: unknown,
+): [string, Record<string, unknown>] | null {
+  if (!entry || typeof entry !== "object") return null;
+  return unwrapTagged(entry as Record<string, unknown>);
+}
+
+/**
+ * Iterate over all download entries for a given node, yielding [tag, payload, modelId].
+ */
+function* iterNodeDownloads(
+  nodeDownloads: unknown[],
+): Generator<[string, Record<string, unknown>, string]> {
+  for (const entry of nodeDownloads) {
+    const tagged = getDownloadTag(entry);
+    if (!tagged) continue;
+    const [tag, payload] = tagged;
+    const modelId = extractModelIdFromDownload(payload);
+    if (!modelId) continue;
+    yield [tag, payload, modelId];
+  }
+}
+
+/** Check if a specific model is fully downloaded (DownloadCompleted) on a specific node. */
+export function isModelDownloadedOnNode(
+  downloadsData: Record<string, unknown[]>,
+  nodeId: string,
+  modelId: string,
+): boolean {
+  const nodeDownloads = downloadsData[nodeId];
+  if (!Array.isArray(nodeDownloads)) return false;
+
+  for (const [tag, , entryModelId] of iterNodeDownloads(nodeDownloads)) {
+    if (tag === "DownloadCompleted" && entryModelId === modelId) return true;
+  }
+  return false;
+}
+
+/** Get all node IDs where a model is fully downloaded (DownloadCompleted). */
+export function getNodesWithModelDownloaded(
+  downloadsData: Record<string, unknown[]>,
+  modelId: string,
+): string[] {
+  const result: string[] = [];
+  for (const nodeId of Object.keys(downloadsData)) {
+    if (isModelDownloadedOnNode(downloadsData, nodeId, modelId)) {
+      result.push(nodeId);
+    }
+  }
+  return result;
+}
+
+/**
+ * Find shard metadata for a model from any download entry across all nodes.
+ * Returns the first match found (completed entries are preferred).
+ */
+export function getShardMetadataForModel(
+  downloadsData: Record<string, unknown[]>,
+  modelId: string,
+): Record<string, unknown> | null {
+  let fallback: Record<string, unknown> | null = null;
+
+  for (const nodeDownloads of Object.values(downloadsData)) {
+    if (!Array.isArray(nodeDownloads)) continue;
+
+    for (const [tag, payload, entryModelId] of iterNodeDownloads(
+      nodeDownloads,
+    )) {
+      if (entryModelId !== modelId) continue;
+      const shard = extractShardMetadata(payload);
+      if (!shard) continue;
+
+      if (tag === "DownloadCompleted") return shard;
+      if (!fallback) fallback = shard;
+    }
+  }
+  return fallback;
+}
+
+/**
+ * Get the download status tag for a specific model on a specific node.
+ * Returns the "best" status: DownloadCompleted > DownloadOngoing > others.
+ */
+export function getModelDownloadStatus(
+  downloadsData: Record<string, unknown[]>,
+  nodeId: string,
+  modelId: string,
+): string | null {
+  const nodeDownloads = downloadsData[nodeId];
+  if (!Array.isArray(nodeDownloads)) return null;
+
+  let best: string | null = null;
+  for (const [tag, , entryModelId] of iterNodeDownloads(nodeDownloads)) {
+    if (entryModelId !== modelId) continue;
+    if (tag === "DownloadCompleted") return tag;
+    if (tag === "DownloadOngoing") best = tag;
+    else if (!best) best = tag;
+  }
+  return best;
+}

dashboard/src/routes/downloads/+page.svelte

@@ -3,6 +3,7 @@
   import {
     topologyData,
     downloads,
+    nodeDisk,
     type DownloadProgress,
     refreshState,
     lastUpdate as lastUpdateStore,
@@ -37,10 +38,13 @@
     nodeId: string;
     nodeName: string;
     models: ModelEntry[];
+    diskAvailable?: number;
+    diskTotal?: number;
   };
 
   const data = $derived(topologyData());
   const downloadsData = $derived(downloads());
+  const nodeDiskData = $derived(nodeDisk());
 
   function getNodeLabel(nodeId: string): string {
     const node = data?.nodes?.[nodeId];
@@ -327,10 +331,17 @@
           ];
         }
 
+        // Get disk info for this node
+        const diskInfo = nodeDiskData?.[nodeId];
+        const diskAvailable = diskInfo?.available?.inBytes;
+        const diskTotal = diskInfo?.total?.inBytes;
+
         built.push({
           nodeId,
           nodeName: getNodeLabel(nodeId),
           models,
+          diskAvailable,
+          diskTotal,
         });
       }
 
@@ -417,6 +428,14 @@
                 <div class="text-xs text-exo-light-gray font-mono truncate">
                   {node.nodeId}
                 </div>
+                <div class="text-xs text-exo-light-gray font-mono mt-1">
+                  {formatBytes(
+                    node.models
+                      .filter((m) => m.status === "completed")
+                      .reduce((sum, m) => sum + m.totalBytes, 0),
+                  )} models{#if node.diskAvailable != null}
+                    - {formatBytes(node.diskAvailable)} free{/if}
+                </div>
               </div>
               <div
                 class="text-xs font-mono uppercase tracking-wider whitespace-nowrap shrink-0 text-right"
@@ -429,13 +448,6 @@
                     / {node.models.length} models</span
                   >
                 </div>
-                <div class="text-exo-light-gray normal-case tracking-normal">
-                  {formatBytes(
-                    node.models
-                      .filter((m) => m.status === "completed")
-                      .reduce((sum, m) => sum + m.totalBytes, 0),
-                  )} on disk
-                </div>
               </div>
             </div>
 

e2e/Dockerfile

@@ -0,0 +1,58 @@
+# Stage 1: Build the dashboard
+FROM node:22-slim AS dashboard
+WORKDIR /app/dashboard
+COPY dashboard/package.json dashboard/package-lock.json ./
+RUN npm ci
+COPY dashboard/ .
+RUN npm run build
+
+# Stage 2: Build and run exo
+FROM python:3.13-slim
+
+# Install system dependencies
+# libblas-dev/liblapack-dev/liblapacke-dev are required by MLX CPU backend on Linux
+RUN apt-get update && apt-get install -y \
+    build-essential \
+    pkg-config \
+    libssl-dev \
+    libblas-dev \
+    liblapack-dev \
+    liblapacke-dev \
+    curl \
+    protobuf-compiler \
+    iptables \
+    && rm -rf /var/lib/apt/lists/*
+
+# Install Rust nightly
+RUN curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y --default-toolchain nightly
+ENV PATH="/root/.cargo/bin:${PATH}"
+
+# Wrap g++ with -fpermissive to fix MLX CPU JIT compilation with GCC 14
+# (GCC 14 treats _Float128/_Float32/_Float64 as built-in types, conflicting with MLX-generated code)
+# Must be done BEFORE uv sync so any source builds also get the fix
+RUN mv /usr/bin/g++ /usr/bin/g++.real && \
+    printf '#!/bin/sh\nexec /usr/bin/g++.real -fpermissive "$@"\n' > /usr/bin/g++ && \
+    chmod +x /usr/bin/g++
+
+# Install uv
+COPY --from=ghcr.io/astral-sh/uv:latest /uv /usr/local/bin/uv
+
+WORKDIR /app
+
+# Copy dependency files first for better layer caching
+COPY pyproject.toml Cargo.toml uv.lock README.md ./
+COPY rust/ ./rust/
+COPY bench/pyproject.toml ./bench/pyproject.toml
+
+# Copy source and resources
+COPY src/ ./src/
+COPY resources/ ./resources/
+
+# Copy built dashboard from stage 1
+COPY --from=dashboard /app/dashboard/build ./dashboard/build/
+
+# Install Python deps and build Rust bindings, then clean up build artifacts
+# to keep the layer small (Rust target/ and cargo registry can be 1-2 GB)
+RUN uv sync && rm -rf /app/rust/target /root/.cargo/registry /root/.cargo/git
+
+CMD [".venv/bin/exo", "-v"]

e2e/conftest.py

@@ -0,0 +1,195 @@
+"""Shared E2E test infrastructure for exo cluster tests."""
+
+import asyncio
+import json
+import os
+import sys
+from pathlib import Path
+from urllib.error import URLError
+from urllib.request import Request, urlopen
+
+E2E_DIR = Path(__file__).parent.resolve()
+TIMEOUT = int(os.environ.get("E2E_TIMEOUT", "120"))
+
+
+class Cluster:
+    """Async wrapper around a docker compose exo cluster."""
+
+    def __init__(self, name: str, overrides: list[str] | None = None):
+        self.name = name
+        self.project = f"e2e-{name}"
+        compose_files = [str(E2E_DIR / "docker-compose.yml")]
+        for path in overrides or []:
+            compose_files.append(str(E2E_DIR / path))
+        self._compose_base = [
+            "docker",
+            "compose",
+            "-p",
+            self.project,
+            *[arg for f in compose_files for arg in ("-f", f)],
+        ]
+
+    async def __aenter__(self):
+        return self
+
+    async def __aexit__(self, *exc):
+        await self.stop()
+
+    async def _run(self, *args: str, check: bool = True) -> str:
+        proc = await asyncio.create_subprocess_exec(
+            *self._compose_base,
+            *args,
+            stdout=asyncio.subprocess.PIPE,
+            stderr=asyncio.subprocess.STDOUT,
+        )
+        stdout, _ = await proc.communicate()
+        output = stdout.decode()
+        if check and proc.returncode != 0:
+            print(output, file=sys.stderr)
+            raise RuntimeError(
+                f"docker compose {' '.join(args)} failed (rc={proc.returncode})"
+            )
+        return output
+
+    async def build(self):
+        # Skip build if the image was pre-built (e.g. in CI with buildx cache)
+        proc = await asyncio.create_subprocess_exec(
+            "docker",
+            "image",
+            "inspect",
+            "exo-e2e:latest",
+            stdout=asyncio.subprocess.DEVNULL,
+            stderr=asyncio.subprocess.DEVNULL,
+        )
+        await proc.wait()
+        if proc.returncode == 0:
+            print("  Using pre-built image (exo-e2e:latest)")
+            return
+        print("  Building images...")
+        await self._run("build", "--quiet")
+
+    async def start(self):
+        print("  Starting cluster...")
+        await self._run("up", "-d")
+
+    async def stop(self):
+        print("  Cleaning up...")
+        await self._run("down", "--timeout", "5", check=False)
+
+    async def logs(self) -> str:
+        return await self._run("logs", check=False)
+
+    async def exec(
+        self, service: str, *cmd: str, check: bool = True
+    ) -> tuple[int, str]:
+        """Run a command inside a running container. Returns (returncode, output)."""
+        proc = await asyncio.create_subprocess_exec(
+            *self._compose_base,
+            "exec",
+            "-T",
+            service,
+            *cmd,
+            stdout=asyncio.subprocess.PIPE,
+            stderr=asyncio.subprocess.STDOUT,
+        )
+        stdout, _ = await proc.communicate()
+        output = stdout.decode()
+        if check and proc.returncode != 0:
+            raise RuntimeError(
+                f"exec {' '.join(cmd)} in {service} failed (rc={proc.returncode})"
+            )
+        return proc.returncode, output
+
+    async def wait_for(self, description: str, check_fn, timeout: int = TIMEOUT):
+        """Poll check_fn every 2s until it returns True or timeout expires."""
+        print(f"  Waiting for {description}...")
+        deadline = asyncio.get_event_loop().time() + timeout
+        while asyncio.get_event_loop().time() < deadline:
+            if await check_fn():
+                print(f"  {description}")
+                return
+            await asyncio.sleep(2)
+        output = await self.logs()
+        print(f"--- cluster logs ---\n{output}\n---", file=sys.stderr)
+        raise TimeoutError(f"Timed out waiting for {description}")
+
+    async def assert_healthy(self):
+        """Verify the cluster formed correctly: nodes started, discovered each other, elected a master, API responds."""
+
+        async def both_nodes_started():
+            log = await self.logs()
+            return log.count("Starting node") >= 2
+
+        async def nodes_discovered():
+            log = await self.logs()
+            return log.count("ConnectionMessageType.Connected") >= 2
+
+        async def master_elected():
+            log = await self.logs()
+            return "demoting self" in log
+
+        async def api_responding():
+            try:
+                with urlopen("http://localhost:52415/v1/models", timeout=3) as resp:
+                    return resp.status == 200
+            except (URLError, OSError):
+                return False
+
+        await self.wait_for("Both nodes started", both_nodes_started)
+        await self.wait_for("Nodes discovered each other", nodes_discovered)
+        await self.wait_for("Master election resolved", master_elected)
+        await self.wait_for("API responding", api_responding)
+
+    async def _api(
+        self, method: str, path: str, body: dict | None = None, timeout: int = 30
+    ) -> dict:
+        """Make an API request to the cluster. Returns parsed JSON."""
+        url = f"http://localhost:52415{path}"
+        data = json.dumps(body).encode() if body else None
+        req = Request(
+            url, data=data, headers={"Content-Type": "application/json"}, method=method
+        )
+        loop = asyncio.get_event_loop()
+        resp_bytes = await loop.run_in_executor(
+            None, lambda: urlopen(req, timeout=timeout).read()
+        )
+        return json.loads(resp_bytes)
+
+    async def place_model(self, model: str, timeout: int = 600):
+        """Place a model instance on the cluster (triggers download) and wait until it's ready."""
+        await self._api("POST", "/place_instance", {"model_id": model})
+
+        async def model_ready():
+            try:
+                resp = await self._api("GET", "/v1/models")
+                return any(m.get("id") == model for m in resp.get("data", []))
+            except Exception:
+                return False
+
+        await self.wait_for(f"Model {model} ready", model_ready, timeout=timeout)
+
+    async def chat(
+        self, model: str, messages: list[dict], timeout: int = 600, **kwargs
+    ) -> dict:
+        """Send a chat completion request. Retries until model is downloaded and inference completes."""
+        body = json.dumps({"model": model, "messages": messages, **kwargs}).encode()
+        deadline = asyncio.get_event_loop().time() + timeout
+        last_error = None
+
+        while asyncio.get_event_loop().time() < deadline:
+            try:
+                req = Request(
+                    "http://localhost:52415/v1/chat/completions",
+                    data=body,
+                    headers={"Content-Type": "application/json"},
+                )
+                loop = asyncio.get_event_loop()
+                resp_bytes = await loop.run_in_executor(
+                    None, lambda r=req: urlopen(r, timeout=300).read()
+                )
+                return json.loads(resp_bytes)
+            except Exception as e:
+                last_error = e
+                await asyncio.sleep(5)
+
+        raise TimeoutError(f"Chat request failed after {timeout}s: {last_error}")

e2e/docker-compose.yml

@@ -0,0 +1,20 @@
+services:
+  exo-node-1:
+    image: exo-e2e:latest
+    build:
+      context: ..
+      dockerfile: e2e/Dockerfile
+    environment:
+      - EXO_LIBP2P_NAMESPACE=docker-e2e
+    command: [".venv/bin/exo", "-v"]
+    ports:
+      - "52415:52415"
+
+  exo-node-2:
+    image: exo-e2e:latest
+    build:
+      context: ..
+      dockerfile: e2e/Dockerfile
+    environment:
+      - EXO_LIBP2P_NAMESPACE=docker-e2e
+    command: [".venv/bin/exo", "-v"]

e2e/run_all.py

@@ -0,0 +1,83 @@
+#!/usr/bin/env python3
+"""Discovers and runs all E2E tests in e2e/test_*.py.
+
+Tests with '# slow' on the first line of their docstring are skipped
+unless --slow is passed or E2E_SLOW=1 is set.
+"""
+
+import os
+import subprocess
+import sys
+from pathlib import Path
+
+E2E_DIR = Path(__file__).parent.resolve()
+
+
+def is_slow(test_file: Path) -> bool:
+    """Check if the test file is marked as slow (has '# slow' in first 3 lines)."""
+    with open(test_file) as f:
+        for line in f:
+            if line.strip().startswith("#"):
+                continue
+            if line.strip().startswith('"""') or line.strip().startswith("'''"):
+                # Read into the docstring
+                for doc_line in f:
+                    if "slow" in doc_line.lower() and doc_line.strip().startswith(
+                        "slow"
+                    ):
+                        return True
+                    if '"""' in doc_line or "'''" in doc_line:
+                        break
+            break
+    return False
+
+
+def main():
+    run_slow = "--slow" in sys.argv or os.environ.get("E2E_SLOW") == "1"
+    if "--update-snapshots" in sys.argv:
+        os.environ["UPDATE_SNAPSHOTS"] = "1"
+    test_files = sorted(E2E_DIR.glob("test_*.py"))
+    if not test_files:
+        print("No test files found")
+        sys.exit(1)
+
+    passed = 0
+    failed = 0
+    skipped = 0
+    failures = []
+
+    for test_file in test_files:
+        name = test_file.stem
+        if is_slow(test_file) and not run_slow:
+            print(f"=== {name} === SKIPPED (slow, use --slow to run)")
+            skipped += 1
+            continue
+
+        print(f"=== {name} ===")
+        result = subprocess.run([sys.executable, str(test_file)])
+        if result.returncode == 0:
+            passed += 1
+        else:
+            # Retry once — Docker networking (mDNS) can be slow on first boot
+            print(f"\n=== {name} === RETRYING (attempt 2/2)")
+            result = subprocess.run([sys.executable, str(test_file)])
+            if result.returncode == 0:
+                passed += 1
+            else:
+                failed += 1
+                failures.append(name)
+        print()
+
+    total = passed + failed + skipped
+    print("================================")
+    print(
+        f"{passed}/{total} tests passed" + (f", {skipped} skipped" if skipped else "")
+    )
+
+    if failed:
+        print(f"Failed: {' '.join(failures)}")
+        sys.exit(1)
+
+
+if __name__ == "__main__":
+    main()

e2e/snapshot.py

@@ -0,0 +1,78 @@
+"""Snapshot testing infrastructure for E2E tests.
+
+Provides deterministic regression testing by comparing inference output
+against committed baseline snapshots. Tests FAIL if no baseline exists —
+baselines must be explicitly generated and committed.
+
+Generate baselines: UPDATE_SNAPSHOTS=1 python3 e2e/run_all.py --slow
+Update after intentional changes: UPDATE_SNAPSHOTS=1 python3 e2e/run_all.py --slow
+
+Snapshots are stored per-architecture (e.g. snapshots/x86_64/, snapshots/arm64/)
+since floating-point results differ between CPU architectures.
+"""
+
+import difflib
+import json
+import os
+import platform
+from pathlib import Path
+
+ARCH = platform.machine()
+SNAPSHOTS_DIR = Path(__file__).parent / "snapshots" / ARCH
+
+
+def assert_snapshot(
+    name: str,
+    content: str,
+    metadata: dict,
+) -> None:
+    """Compare content against a saved snapshot, or create one if missing.
+
+    Args:
+        name: Snapshot identifier (used as filename: snapshots/{arch}/{name}.json).
+        content: The actual inference output to compare.
+        metadata: Additional context stored alongside content (model, seed, etc.).
+                  Not used for comparison -- purely documentary.
+
+    Raises:
+        AssertionError: If content doesn't match the saved snapshot.
+
+    Environment:
+        UPDATE_SNAPSHOTS=1: Overwrite existing snapshot with actual content.
+    """
+    snapshot_file = SNAPSHOTS_DIR / f"{name}.json"
+    update = os.environ.get("UPDATE_SNAPSHOTS") == "1"
+
+    if update:
+        # Explicitly regenerate snapshot
+        SNAPSHOTS_DIR.mkdir(parents=True, exist_ok=True)
+        snapshot_data = {**metadata, "arch": ARCH, "content": content}
+        snapshot_file.write_text(json.dumps(snapshot_data, indent=2) + "\n")
+        print(f"  Updated snapshot: {ARCH}/{snapshot_file.name}")
+    elif not snapshot_file.exists():
+        raise AssertionError(
+            f"No baseline snapshot for '{name}' on {ARCH}.\n"
+            f"Expected file: {snapshot_file}\n\n"
+            f"Generate baselines with: UPDATE_SNAPSHOTS=1 python3 e2e/run_all.py --slow"
+        )
+    else:
+        snapshot = json.loads(snapshot_file.read_text())
+        expected = snapshot["content"]
+        if content != expected:
+            diff = "\n".join(
+                difflib.unified_diff(
+                    expected.splitlines(),
+                    content.splitlines(),
+                    fromfile=f"expected ({snapshot_file.relative_to(SNAPSHOTS_DIR.parent.parent)})",
+                    tofile="actual",
+                    lineterm="",
+                )
+            )
+            raise AssertionError(
+                f"Snapshot mismatch for '{name}' on {ARCH}!\n\n"
+                f"{diff}\n\n"
+                f"Expected: {expected!r}\n"
+                f"Actual:   {content!r}\n\n"
+                f"To update: UPDATE_SNAPSHOTS=1 python3 e2e/run_all.py --slow"
+            )
+        print(f"  Output matches snapshot ({ARCH}/{snapshot_file.name})")

e2e/test_cluster_formation.py

@@ -0,0 +1,22 @@
+"""Test: Basic cluster formation.
+
+Verifies two nodes discover each other, elect a master, and the API responds.
+"""
+
+import asyncio
+import sys
+
+sys.path.insert(0, str(__import__("pathlib").Path(__file__).parent))
+from conftest import Cluster
+
+
+async def main():
+    async with Cluster("cluster_formation") as cluster:
+        await cluster.build()
+        await cluster.start()
+        await cluster.assert_healthy()
+        print("PASSED: cluster_formation")
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

e2e/test_inference_snapshot.py

@@ -0,0 +1,61 @@
+"""Test: Deterministic inference output (snapshot test).
+
+Sends a chat completion request with a fixed seed,
+then verifies the output matches a known-good snapshot. This ensures
+inference produces consistent results across runs.
+
+Uses MLX CPU backend in Docker on x86 Linux.
+"""
+
+import asyncio
+import sys
+from pathlib import Path
+
+sys.path.insert(0, str(Path(__file__).parent))
+from snapshot import assert_snapshot
+
+from conftest import Cluster
+
+MODEL = "mlx-community/Qwen3-0.6B-4bit"
+SEED = 42
+PROMPT = "What is 2+2? Reply with just the number."
+MAX_TOKENS = 32
+
+
+async def main():
+    async with Cluster("inference_snapshot") as cluster:
+        await cluster.build()
+        await cluster.start()
+        await cluster.assert_healthy()
+
+        print(f"  Launching model {MODEL}...")
+        await cluster.place_model(MODEL)
+
+        print(f"  Sending chat completion (seed={SEED})...")
+        resp = await cluster.chat(
+            model=MODEL,
+            messages=[{"role": "user", "content": PROMPT}],
+            seed=SEED,
+            temperature=0,
+            max_tokens=MAX_TOKENS,
+        )
+
+        content = resp["choices"][0]["message"]["content"]
+        print(f"  Response: {content!r}")
+
+        assert_snapshot(
+            name="inference_snapshot",
+            content=content,
+            metadata={
+                "model": MODEL,
+                "seed": SEED,
+                "prompt": PROMPT,
+                "max_tokens": MAX_TOKENS,
+            },
+        )
+
+        print("PASSED: inference_snapshot")
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

e2e/test_no_internet.py

@@ -0,0 +1,47 @@
+"""Test: Cluster works without internet access.
+
+Verifies exo functions correctly when containers can talk to each other
+but cannot reach the internet. Uses iptables to block all outbound traffic
+except private subnets and multicast (for mDNS discovery).
+"""
+
+import asyncio
+import sys
+
+sys.path.insert(0, str(__import__("pathlib").Path(__file__).parent))
+from conftest import Cluster
+
+
+async def main():
+    async with Cluster(
+        "no_internet",
+        overrides=["tests/no_internet/docker-compose.override.yml"],
+    ) as cluster:
+        await cluster.build()
+        await cluster.start()
+        await cluster.assert_healthy()
+
+        # Verify internet is actually blocked from inside the containers
+        for node in ["exo-node-1", "exo-node-2"]:
+            rc, _ = await cluster.exec(
+                node,
+                "curl",
+                "-sf",
+                "--max-time",
+                "3",
+                "https://huggingface.co",
+                check=False,
+            )
+            assert rc != 0, f"{node} should not be able to reach the internet"
+            print(f"  {node}: internet correctly blocked")
+
+        # Verify exo detected no internet connectivity
+        log = await cluster.logs()
+        assert "Internet connectivity: False" in log, "exo should detect no internet"
+        print("  exo correctly detected no internet connectivity")
+
+        print("PASSED: no_internet")
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

e2e/test_runner_chaos.py

@@ -0,0 +1,65 @@
+"""Test: Runner chaos — abrupt runner death detection.
+slow
+
+Sends a chat completion with the EXO_RUNNER_MUST_DIE trigger, which causes
+the runner process to call os._exit(1) (simulating an OOM kill). Verifies that
+the RunnerSupervisor health check detects the death and the system doesn't hang.
+
+Requires a machine that can run MLX inference at reasonable speed (Apple Silicon).
+Run with: python3 e2e/run_all.py --slow  or  E2E_SLOW=1 python3 e2e/run_all.py
+"""
+
+import asyncio
+import contextlib
+import sys
+from pathlib import Path
+
+sys.path.insert(0, str(Path(__file__).parent))
+from conftest import Cluster
+
+MODEL = "mlx-community/Qwen3-0.6B-4bit"
+
+
+async def main():
+    async with Cluster("runner_chaos") as cluster:
+        await cluster.build()
+        await cluster.start()
+        await cluster.assert_healthy()
+
+        # Place the model so a runner is loaded and ready
+        print(f"  Launching model {MODEL}...")
+        await cluster.place_model(MODEL)
+
+        # Send a chat request with the die trigger.
+        # The runner will call os._exit(1) mid-inference, simulating OOM kill.
+        # The chat request itself will fail — that's expected.
+        print("  Sending EXO_RUNNER_MUST_DIE trigger...")
+        with contextlib.suppress(Exception):
+            await cluster.chat(
+                model=MODEL,
+                messages=[{"role": "user", "content": "EXO RUNNER MUST DIE"}],
+                timeout=60,
+            )
+
+        # Wait for the health check to detect the death and emit RunnerFailed
+        async def health_check_detected():
+            log = await cluster.logs()
+            return "runner process died unexpectedly" in log
+
+        await cluster.wait_for(
+            "Health check detected runner death",
+            health_check_detected,
+            timeout=30,
+        )
+
+        # Verify RunnerFailed was emitted (visible in logs)
+        log = await cluster.logs()
+        assert "runner process died unexpectedly" in log, (
+            f"Expected health check to detect runner death but it didn't.\nLogs:\n{log}"
+        )
+
+        print("PASSED: runner_chaos")
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

e2e/test_snapshot_code_gen.py

@@ -0,0 +1,60 @@
+"""Test: Code generation snapshot.
+slow
+
+Verifies deterministic output for a code generation prompt.
+"""
+
+import asyncio
+import sys
+from pathlib import Path
+
+sys.path.insert(0, str(Path(__file__).parent))
+from snapshot import assert_snapshot
+
+from conftest import Cluster
+
+MODEL = "mlx-community/Qwen3-0.6B-4bit"
+SEED = 42
+PROMPT = (
+    "Write a Python function to reverse a string. Only output the code, no explanation."
+)
+MAX_TOKENS = 64
+
+
+async def main():
+    async with Cluster("snapshot_code_gen") as cluster:
+        await cluster.build()
+        await cluster.start()
+        await cluster.assert_healthy()
+
+        print(f"  Launching model {MODEL}...")
+        await cluster.place_model(MODEL)
+
+        print(f"  Sending chat completion (seed={SEED})...")
+        resp = await cluster.chat(
+            model=MODEL,
+            messages=[{"role": "user", "content": PROMPT}],
+            seed=SEED,
+            temperature=0,
+            max_tokens=MAX_TOKENS,
+        )
+
+        content = resp["choices"][0]["message"]["content"]
+        print(f"  Response: {content!r}")
+
+        assert_snapshot(
+            name="snapshot_code_gen",
+            content=content,
+            metadata={
+                "model": MODEL,
+                "seed": SEED,
+                "prompt": PROMPT,
+                "max_tokens": MAX_TOKENS,
+            },
+        )
+
+        print("PASSED: snapshot_code_gen")
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

e2e/test_snapshot_edge.py

@@ -0,0 +1,65 @@
+"""Test: Edge case snapshots.
+slow
+
+Verifies deterministic output for edge-case prompts: single word input,
+special characters, and unicode.
+"""
+
+import asyncio
+import sys
+from pathlib import Path
+
+sys.path.insert(0, str(Path(__file__).parent))
+from snapshot import assert_snapshot
+
+from conftest import Cluster
+
+MODEL = "mlx-community/Qwen3-0.6B-4bit"
+SEED = 42
+MAX_TOKENS = 32
+
+CASES = [
+    ("edge_single_word", "Hi"),
+    ("edge_special_chars", "What does 2 * (3 + 4) / 7 - 1 equal? Use <math> tags."),
+    ("edge_unicode", "Translate 'hello' to Japanese, Chinese, and Korean."),
+]
+
+
+async def main():
+    async with Cluster("snapshot_edge") as cluster:
+        await cluster.build()
+        await cluster.start()
+        await cluster.assert_healthy()
+
+        print(f"  Launching model {MODEL}...")
+        await cluster.place_model(MODEL)
+
+        for snapshot_name, prompt in CASES:
+            print(f"  [{snapshot_name}] Sending: {prompt!r}")
+            resp = await cluster.chat(
+                model=MODEL,
+                messages=[{"role": "user", "content": prompt}],
+                seed=SEED,
+                temperature=0,
+                max_tokens=MAX_TOKENS,
+            )
+
+            content = resp["choices"][0]["message"]["content"]
+            print(f"  [{snapshot_name}] Response: {content!r}")
+
+            assert_snapshot(
+                name=snapshot_name,
+                content=content,
+                metadata={
+                    "model": MODEL,
+                    "seed": SEED,
+                    "prompt": prompt,
+                    "max_tokens": MAX_TOKENS,
+                },
+            )
+
+        print("PASSED: snapshot_edge")
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

e2e/test_snapshot_long_output.py

@@ -0,0 +1,58 @@
+"""Test: Longer output snapshot.
+slow
+
+Verifies deterministic output with a higher max_tokens (128).
+"""
+
+import asyncio
+import sys
+from pathlib import Path
+
+sys.path.insert(0, str(Path(__file__).parent))
+from snapshot import assert_snapshot
+
+from conftest import Cluster
+
+MODEL = "mlx-community/Qwen3-0.6B-4bit"
+SEED = 42
+PROMPT = "Explain how a binary search algorithm works."
+MAX_TOKENS = 128
+
+
+async def main():
+    async with Cluster("snapshot_long_output") as cluster:
+        await cluster.build()
+        await cluster.start()
+        await cluster.assert_healthy()
+
+        print(f"  Launching model {MODEL}...")
+        await cluster.place_model(MODEL)
+
+        print(f"  Sending chat completion (seed={SEED}, max_tokens={MAX_TOKENS})...")
+        resp = await cluster.chat(
+            model=MODEL,
+            messages=[{"role": "user", "content": PROMPT}],
+            seed=SEED,
+            temperature=0,
+            max_tokens=MAX_TOKENS,
+        )
+
+        content = resp["choices"][0]["message"]["content"]
+        print(f"  Response: {content!r}")
+
+        assert_snapshot(
+            name="snapshot_long_output",
+            content=content,
+            metadata={
+                "model": MODEL,
+                "seed": SEED,
+                "prompt": PROMPT,
+                "max_tokens": MAX_TOKENS,
+            },
+        )
+
+        print("PASSED: snapshot_long_output")
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

e2e/test_snapshot_multi_model.py

@@ -0,0 +1,73 @@
+"""Test: Multi-model snapshot tests.
+slow
+
+Verifies deterministic output across different model architectures to catch
+model-specific regressions. Each model uses its own snapshot file.
+Run with: python3 e2e/run_all.py --slow  or  E2E_SLOW=1 python3 e2e/run_all.py
+"""
+
+import asyncio
+import sys
+from pathlib import Path
+
+sys.path.insert(0, str(Path(__file__).parent))
+from snapshot import assert_snapshot
+
+from conftest import Cluster
+
+SEED = 42
+PROMPT = "What is the capital of France?"
+MAX_TOKENS = 32
+
+MODELS = [
+    "mlx-community/SmolLM2-135M-Instruct",
+    "mlx-community/Llama-3.2-1B-Instruct-4bit",
+    "mlx-community/gemma-2-2b-it-4bit",
+]
+
+
+async def main():
+    async with Cluster("snapshot_multi_model") as cluster:
+        await cluster.build()
+        await cluster.start()
+        await cluster.assert_healthy()
+
+        for model in MODELS:
+            short_name = (
+                model.split("/")[-1].lower().replace("-", "_").replace(".", "_")
+            )
+            snapshot_name = f"snapshot_multi_{short_name}"
+
+            print(f"  Launching model {model}...")
+            await cluster.place_model(model)
+
+            print(f"  Sending chat completion (seed={SEED})...")
+            resp = await cluster.chat(
+                model=model,
+                messages=[{"role": "user", "content": PROMPT}],
+                seed=SEED,
+                temperature=0,
+                max_tokens=MAX_TOKENS,
+            )
+
+            content = resp["choices"][0]["message"]["content"]
+            print(f"  [{short_name}] Response: {content!r}")
+
+            assert_snapshot(
+                name=snapshot_name,
+                content=content,
+                metadata={
+                    "model": model,
+                    "seed": SEED,
+                    "prompt": PROMPT,
+                    "max_tokens": MAX_TOKENS,
+                },
+            )
+
+            print(f"  [{short_name}] PASSED")
+
+        print("PASSED: snapshot_multi_model")
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

e2e/test_snapshot_reasoning.py

@@ -0,0 +1,58 @@
+"""Test: Reasoning/math snapshot.
+slow
+
+Verifies deterministic output for a simple reasoning prompt.
+"""
+
+import asyncio
+import sys
+from pathlib import Path
+
+sys.path.insert(0, str(Path(__file__).parent))
+from snapshot import assert_snapshot
+
+from conftest import Cluster
+
+MODEL = "mlx-community/Qwen3-0.6B-4bit"
+SEED = 42
+PROMPT = "If I have 3 apples and give away 1, how many do I have? Think step by step."
+MAX_TOKENS = 64
+
+
+async def main():
+    async with Cluster("snapshot_reasoning") as cluster:
+        await cluster.build()
+        await cluster.start()
+        await cluster.assert_healthy()
+
+        print(f"  Launching model {MODEL}...")
+        await cluster.place_model(MODEL)
+
+        print(f"  Sending chat completion (seed={SEED})...")
+        resp = await cluster.chat(
+            model=MODEL,
+            messages=[{"role": "user", "content": PROMPT}],
+            seed=SEED,
+            temperature=0,
+            max_tokens=MAX_TOKENS,
+        )
+
+        content = resp["choices"][0]["message"]["content"]
+        print(f"  Response: {content!r}")
+
+        assert_snapshot(
+            name="snapshot_reasoning",
+            content=content,
+            metadata={
+                "model": MODEL,
+                "seed": SEED,
+                "prompt": PROMPT,
+                "max_tokens": MAX_TOKENS,
+            },
+        )
+
+        print("PASSED: snapshot_reasoning")
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

e2e/tests/no_internet/docker-compose.override.yml

@@ -0,0 +1,32 @@
+# Block all outbound internet traffic using iptables while preserving:
+#   - Multicast (224.0.0.0/4) for mDNS peer discovery
+#   - Private subnets (10/8, 172.16/12, 192.168/16) for inter-container communication
+#   - Loopback (127/8)
+# Requires NET_ADMIN capability for iptables.
+services:
+  exo-node-1:
+    cap_add:
+      - NET_ADMIN
+    entrypoint: ["/bin/sh", "-c"]
+    command:
+      - |
+        iptables -A OUTPUT -d 127.0.0.0/8 -j ACCEPT
+        iptables -A OUTPUT -d 10.0.0.0/8 -j ACCEPT
+        iptables -A OUTPUT -d 172.16.0.0/12 -j ACCEPT
+        iptables -A OUTPUT -d 192.168.0.0/16 -j ACCEPT
+        iptables -A OUTPUT -d 224.0.0.0/4 -j ACCEPT
+        iptables -A OUTPUT -j REJECT
+        exec .venv/bin/exo -v
+  exo-node-2:
+    cap_add:
+      - NET_ADMIN
+    entrypoint: ["/bin/sh", "-c"]
+    command:
+      - |
+        iptables -A OUTPUT -d 127.0.0.0/8 -j ACCEPT
+        iptables -A OUTPUT -d 10.0.0.0/8 -j ACCEPT
+        iptables -A OUTPUT -d 172.16.0.0/12 -j ACCEPT
+        iptables -A OUTPUT -d 192.168.0.0/16 -j ACCEPT
+        iptables -A OUTPUT -d 224.0.0.0/4 -j ACCEPT
+        iptables -A OUTPUT -j REJECT
+        exec .venv/bin/exo -v

flake.nix

@@ -83,6 +83,9 @@
           _module.args.pkgs = import inputs.nixpkgs {
             inherit system;
             config.allowUnfreePredicate = pkg: (pkg.pname or "") == "metal-toolchain";
+            overlays = [
+              (import ./nix/apple-sdk-overlay.nix)
+            ];
           };
           treefmt = {
             projectRootFile = "flake.nix";
@@ -118,9 +121,10 @@
             {
               metal-toolchain = pkgs.callPackage ./nix/metal-toolchain.nix { };
               mlx = pkgs.callPackage ./nix/mlx.nix {
-                metal-toolchain = self'.packages.metal-toolchain;
+                inherit (self'.packages) metal-toolchain;
                 inherit uvLockMlxVersion;
               };
+              default = self'.packages.exo;
             }
           );
 

justfile

@@ -20,7 +20,7 @@ sync-clean:
 
 rust-rebuild:
     cargo run --bin stub_gen
-    just sync-clean
+    uv sync --reinstall-package exo_pyo3_bindings
 
 build-dashboard:
     #!/usr/bin/env bash

nix/apple-sdk-overlay.nix

@@ -0,0 +1,18 @@
+# Overlay that builds apple-sdk with a custom versions.json (for SDK 26.2).
+# The upstream nixpkgs package reads versions.json at eval time via a relative
+# path, so we can't override it through callPackage args. Instead, we copy
+# the upstream source and patch the one file.
+final: _prev:
+let
+  upstreamSrc = final.path + "/pkgs/by-name/ap/apple-sdk";
+  patchedSrc = final.runCommandLocal "apple-sdk-src-patched" { } ''
+    cp -r ${upstreamSrc} $out
+    chmod -R u+w $out
+    cp ${./apple-sdk/metadata/versions.json} $out/metadata/versions.json
+  '';
+in
+{
+  apple-sdk_26 = final.callPackage (patchedSrc + "/package.nix") {
+    darwinSdkMajorVersion = "26";
+  };
+}

nix/apple-sdk/metadata/versions.json

@@ -0,0 +1,26 @@
+{
+  "14": {
+    "urls": [
+      "https://swcdn.apple.com/content/downloads/14/48/052-59890-A_I0F5YGAY0Y/p9n40hio7892gou31o1v031ng6fnm9sb3c/CLTools_macOSNMOS_SDK.pkg",
+      "https://web.archive.org/web/20250211001355/https://swcdn.apple.com/content/downloads/14/48/052-59890-A_I0F5YGAY0Y/p9n40hio7892gou31o1v031ng6fnm9sb3c/CLTools_macOSNMOS_SDK.pkg"
+    ],
+    "version": "14.4",
+    "hash": "sha256-QozDiwY0Czc0g45vPD7G4v4Ra+3DujCJbSads3fJjjM="
+  },
+  "15": {
+    "urls": [
+      "https://swcdn.apple.com/content/downloads/52/01/082-41241-A_0747ZN8FHV/dectd075r63pppkkzsb75qk61s0lfee22j/CLTools_macOSNMOS_SDK.pkg",
+      "https://web.archive.org/web/20250530132510/https://swcdn.apple.com/content/downloads/52/01/082-41241-A_0747ZN8FHV/dectd075r63pppkkzsb75qk61s0lfee22j/CLTools_macOSNMOS_SDK.pkg"
+    ],
+    "version": "15.5",
+    "hash": "sha256-HBiSJuw1XBUK5R/8Sj65c3rftSEvQl/O9ZZVp/g1Amo="
+  },
+  "26": {
+    "urls": [
+      "https://swcdn.apple.com/content/downloads/60/22/089-71960-A_W8BL1RUJJ6/5zkyplomhk1cm7z6xja2ktgapnhhti6wwd/CLTools_macOSNMOS_SDK.pkg",
+      "https://web.archive.org/web/20250915230423/https://swcdn.apple.com/content/downloads/60/22/089-71960-A_W8BL1RUJJ6/5zkyplomhk1cm7z6xja2ktgapnhhti6wwd/CLTools_macOSNMOS_SDK.pkg"
+    ],
+    "version": "26.2",
+    "hash": "sha256-hXRlMieVv0smna5uiWRwq87IWOaPWtAjAldbi+wQXcw="
+  }
+}

nix/mlx.nix

@@ -41,7 +41,7 @@ let
 
   mlx = stdenv.mkDerivation rec {
     pname = "mlx";
-    version = let v = "0.30.4"; in
+    version = let v = "0.30.6"; in
       assert v == uvLockMlxVersion || throw "MLX version mismatch: nix/mlx.nix has ${v} but uv.lock has ${uvLockMlxVersion}. Update both the version and hash in nix/mlx.nix.";
       v;
     pyproject = true;
@@ -50,7 +50,7 @@ let
       owner = "ml-explore";
       repo = "mlx";
       tag = "v${version}";
-      hash = "sha256-OJk6jPlbaSlsUdk3ADz3tWcRzTWXRof3/q8Soe1AO6w=";
+      hash = "sha256-avD5EGhwgmPdXLAyQSqTO6AXk/W3ziH+f6AetjK3Sdo=";
     };
 
     patches = [
@@ -85,6 +85,7 @@ let
         (lib.cmakeOptionType "filepath" "FETCHCONTENT_SOURCE_DIR_JSON" "${nlohmann_json.src}")
         (lib.cmakeOptionType "filepath" "FETCHCONTENT_SOURCE_DIR_NANOBIND" "${nanobind}")
         (lib.cmakeBool "FETCHCONTENT_FULLY_DISCONNECTED" true)
+        (lib.cmakeBool "MLX_BUILD_CPU" true)
         (lib.cmakeBool "MLX_BUILD_METAL" true)
         (lib.cmakeOptionType "filepath" "FETCHCONTENT_SOURCE_DIR_METAL_CPP" "${metal_cpp}")
         (lib.cmakeOptionType "string" "CMAKE_OSX_DEPLOYMENT_TARGET" "${apple-sdk_26.version}")

packaging/pyinstaller/exo.spec

@@ -10,6 +10,7 @@ PROJECT_ROOT = Path.cwd()
 SOURCE_ROOT = PROJECT_ROOT / "src"
 ENTRYPOINT = SOURCE_ROOT / "exo" / "__main__.py"
 DASHBOARD_DIR = PROJECT_ROOT / "dashboard" / "build"
+RESOURCES_DIR = PROJECT_ROOT / "resources"
 EXO_SHARED_MODELS_DIR = SOURCE_ROOT / "exo" / "shared" / "models"
 
 if not ENTRYPOINT.is_file():
@@ -18,6 +19,9 @@ if not ENTRYPOINT.is_file():
 if not DASHBOARD_DIR.is_dir():
     raise SystemExit(f"Dashboard assets are missing: {DASHBOARD_DIR}")
 
+if not RESOURCES_DIR.is_dir():
+    raise SystemExit(f"Resource assets are missing: {RESOURCES_DIR}")
+
 if not EXO_SHARED_MODELS_DIR.is_dir():
     raise SystemExit(f"Shared model assets are missing: {EXO_SHARED_MODELS_DIR}")
 
@@ -58,6 +62,7 @@ HIDDEN_IMPORTS = sorted(
 
 DATAS: list[tuple[str, str]] = [
     (str(DASHBOARD_DIR), "dashboard"),
+    (str(RESOURCES_DIR), "resources"),
     (str(MLX_LIB_DIR), "mlx/lib"),
     (str(EXO_SHARED_MODELS_DIR), "exo/shared/models"),
 ]

pyproject.toml

@@ -17,22 +17,22 @@ dependencies = [
     "loguru>=0.7.3",
     "exo_pyo3_bindings", # rust bindings
     "anyio==4.11.0",
-    "mlx==0.30.4; sys_platform == 'darwin'",
-    "mlx[cpu]==0.30.4; sys_platform == 'linux'",
-    "mlx-lm",
+    "mlx==0.30.6; sys_platform == 'darwin'",
+    "mlx[cpu]==0.30.6; sys_platform == 'linux'",
+    "mlx-lm==0.30.6",
     "tiktoken>=0.12.0", # required for kimi k2 tokenizer
     "hypercorn>=0.18.0",
     "openai-harmony>=0.0.8",
     "httpx>=0.28.1",
     "tomlkit>=0.14.0",
     "pillow>=11.0,<12.0", # compatibility with mflux
-    "mflux==0.15.4",
+    "mflux==0.15.5",
     "python-multipart>=0.0.21",
+    "msgspec>=0.19.0",
+    "zstandard>=0.23.0",
 ]
 
 [project.scripts]
-exo-master = "exo.master.main:main"
-exo-worker = "exo.worker.main:main"
 exo = "exo.main:main"
 
 # dependencies only required for development
@@ -59,11 +59,12 @@ dev = [
 [tool.uv.workspace]
 members = [
     "rust/exo_pyo3_bindings",
+    "bench",
 ]
 
 [tool.uv.sources]
 exo_pyo3_bindings = { workspace = true }
-mlx-lm = { git = "https://github.com/ml-explore/mlx-lm", branch = "main" }
+#mlx-lm = { git = "https://github.com/davidmcc73/mlx-lm", branch = "stable" }
 # Uncomment to use local mlx/mlx-lm development versions:
 # mlx = { path = "/Users/Shared/mlx", editable=true }
 # mlx-lm = { path = "/Users/Shared/mlx-lm", editable=true }
@@ -105,6 +106,7 @@ root = "src"
 
 # supported platforms for this project
 [tool.uv]
+required-version = ">=0.8.6"
 prerelease = "allow"
 environments = [
     "sys_platform == 'darwin'",

python/parts.nix

@@ -14,7 +14,9 @@
 
       # Override overlay to inject Nix-built components
       exoOverlay = final: prev: {
-        # Replace workspace exo_pyo3_bindings with Nix-built wheel
+        # Replace workspace exo_pyo3_bindings with Nix-built wheel.
+        # Preserve passthru so mkVirtualEnv can resolve dependency groups.
+        # Copy .pyi stub + py.typed marker so basedpyright can find the types.
         exo-pyo3-bindings = pkgs.stdenv.mkDerivation {
           pname = "exo-pyo3-bindings";
           version = "0.1.0";
@@ -22,6 +24,12 @@
           # Install from pre-built wheel
           nativeBuildInputs = [ final.pyprojectWheelHook ];
           dontStrip = true;
+          passthru = prev.exo-pyo3-bindings.passthru or { };
+          postInstall = ''
+            local siteDir=$out/${final.python.sitePackages}/exo_pyo3_bindings
+            cp ${inputs.self}/rust/exo_pyo3_bindings/exo_pyo3_bindings.pyi $siteDir/
+            touch $siteDir/py.typed
+          '';
         };
       };
 
@@ -29,17 +37,32 @@
 
       # Overlay to provide build systems and custom packages
       buildSystemsOverlay = final: prev: {
-        # Use our pure Nix-built MLX with Metal support
-        mlx = self'.packages.mlx;
-
         # mlx-lm is a git dependency that needs setuptools
         mlx-lm = prev.mlx-lm.overrideAttrs (old: {
           nativeBuildInputs = (old.nativeBuildInputs or [ ]) ++ [
             final.setuptools
           ];
         });
+      } // lib.optionalAttrs pkgs.stdenv.hostPlatform.isDarwin {
+        # Use our pure Nix-built MLX with Metal support (macOS only)
+        mlx = self'.packages.mlx;
       };
 
+      # Additional overlay for Linux-specific fixes (type checking env).
+      # Native wheels have shared lib dependencies we don't need at type-check time.
+      linuxOverlay = final: prev:
+        let
+          ignoreMissing = drv: drv.overrideAttrs { autoPatchelfIgnoreMissingDeps = [ "*" ]; };
+          nvidiaPackages = lib.filterAttrs (name: _: lib.hasPrefix "nvidia-" name) prev;
+        in
+        lib.optionalAttrs pkgs.stdenv.hostPlatform.isLinux (
+          (lib.mapAttrs (_: ignoreMissing) nvidiaPackages) // {
+            mlx = ignoreMissing prev.mlx;
+            torch = ignoreMissing prev.torch;
+            triton = ignoreMissing prev.triton;
+          }
+        );
+
       pythonSet = (pkgs.callPackage inputs.pyproject-nix.build.packages {
         inherit python;
       }).overrideScope (
@@ -48,6 +71,7 @@
           overlay
           exoOverlay
           buildSystemsOverlay
+          linuxOverlay
         ]
       );
       exoVenv = pythonSet.mkVirtualEnv "exo-env" workspace.deps.default;
@@ -59,6 +83,32 @@
         }
       );
 
+      mkPythonScript = name: path: pkgs.writeShellApplication {
+        inherit name;
+        runtimeInputs = [ exoVenv ];
+        runtimeEnv = {
+          EXO_DASHBOARD_DIR = self'.packages.dashboard;
+          EXO_RESOURCES_DIR = inputs.self + /resources;
+        };
+        text = ''exec python ${path} "$@"'';
+      };
+
+      benchVenv = pythonSet.mkVirtualEnv "exo-bench-env" {
+        exo-bench = [ ];
+      };
+
+      mkBenchScript = name: path: pkgs.writeShellApplication {
+        inherit name;
+        runtimeInputs = [ benchVenv ];
+        text = ''exec python ${path} "$@"'';
+      };
+
+      mkSimplePythonScript = name: path: pkgs.writeShellApplication {
+        inherit name;
+        runtimeInputs = [ pkgs.python313 ];
+        text = ''exec python ${path} "$@"'';
+      };
+
       exoPackage = pkgs.runCommand "exo"
         {
           nativeBuildInputs = [ pkgs.makeWrapper ];
@@ -66,29 +116,47 @@
         ''
           mkdir -p $out/bin
 
-          # Create wrapper scripts
-          for script in exo exo-master exo-worker; do
-            makeWrapper ${exoVenv}/bin/$script $out/bin/$script \
-              --set DASHBOARD_DIR ${self'.packages.dashboard} \
-              ${lib.optionalString pkgs.stdenv.isDarwin "--prefix PATH : ${pkgs.macmon}/bin"}
-          done
+          # Create wrapper script
+          makeWrapper ${exoVenv}/bin/exo $out/bin/exo \
+            --set EXO_DASHBOARD_DIR ${self'.packages.dashboard} \
+            --set EXO_RESOURCES_DIR ${inputs.self + /resources} \
+            ${lib.optionalString pkgs.stdenv.hostPlatform.isDarwin "--prefix PATH : ${pkgs.macmon}/bin"}
         '';
     in
     {
       # Python package only available on macOS (requires MLX/Metal)
-      packages = lib.optionalAttrs pkgs.stdenv.hostPlatform.isDarwin {
-        exo = exoPackage;
-        # Test environment for running pytest outside of Nix sandbox (needs GPU access)
-        exo-test-env = testVenv;
+      packages = lib.optionalAttrs pkgs.stdenv.hostPlatform.isDarwin
+        {
+          exo = exoPackage;
+          # Test environment for running pytest outside of Nix sandbox (needs GPU access)
+          exo-test-env = testVenv;
+        } // {
+        exo-bench = mkBenchScript "exo-bench" (inputs.self + /bench/exo_bench.py);
+        exo-get-all-models-on-cluster = mkSimplePythonScript "exo-get-all-models-on-cluster" (inputs.self + /tests/get_all_models_on_cluster.py);
       };
 
       checks = {
         # Ruff linting (works on all platforms)
         lint = pkgs.runCommand "ruff-lint" { } ''
           export RUFF_CACHE_DIR="$TMPDIR/ruff-cache"
-          ${pkgs.ruff}/bin/ruff check ${inputs.self}/
+          ${pkgs.ruff}/bin/ruff check ${inputs.self}
           touch $out
         '';
+
+        # Hermetic basedpyright type checking
+        typecheck = pkgs.runCommand "typecheck"
+          {
+            nativeBuildInputs = [
+              testVenv
+              pkgs.basedpyright
+            ];
+          }
+          ''
+            cd ${inputs.self}
+            export HOME=$TMPDIR
+            basedpyright --pythonpath ${testVenv}/bin/python
+            touch $out
+          '';
       };
     };
 }

resources/image_model_cards/exolabs--FLUX.1-Kontext-dev-4bit.toml

@@ -0,0 +1,49 @@
+model_id = "exolabs/FLUX.1-Kontext-dev-4bit"
+n_layers = 57
+hidden_size = 1
+supports_tensor = false
+tasks = ["ImageToImage"]
+family = "flux"
+quantization = "4bit"
+base_model = "FLUX.1 Kontext"
+capabilities = ["image_edit"]
+
+[storage_size]
+in_bytes = 15475325472
+
+[[components]]
+component_name = "text_encoder"
+component_path = "text_encoder/"
+n_layers = 12
+can_shard = false
+
+[components.storage_size]
+in_bytes = 0
+
+[[components]]
+component_name = "text_encoder_2"
+component_path = "text_encoder_2/"
+n_layers = 24
+can_shard = false
+safetensors_index_filename = "model.safetensors.index.json"
+
+[components.storage_size]
+in_bytes = 9524621312
+
+[[components]]
+component_name = "transformer"
+component_path = "transformer/"
+n_layers = 57
+can_shard = true
+safetensors_index_filename = "diffusion_pytorch_model.safetensors.index.json"
+
+[components.storage_size]
+in_bytes = 5950704160
+
+[[components]]
+component_name = "vae"
+component_path = "vae/"
+can_shard = false
+
+[components.storage_size]
+in_bytes = 0

resources/image_model_cards/exolabs--FLUX.1-Kontext-dev-8bit.toml

@@ -0,0 +1,49 @@
+model_id = "exolabs/FLUX.1-Kontext-dev-8bit"
+n_layers = 57
+hidden_size = 1
+supports_tensor = false
+tasks = ["ImageToImage"]
+family = "flux"
+quantization = "8bit"
+base_model = "FLUX.1 Kontext"
+capabilities = ["image_edit"]
+
+[storage_size]
+in_bytes = 21426029632
+
+[[components]]
+component_name = "text_encoder"
+component_path = "text_encoder/"
+n_layers = 12
+can_shard = false
+
+[components.storage_size]
+in_bytes = 0
+
+[[components]]
+component_name = "text_encoder_2"
+component_path = "text_encoder_2/"
+n_layers = 24
+can_shard = false
+safetensors_index_filename = "model.safetensors.index.json"
+
+[components.storage_size]
+in_bytes = 9524621312
+
+[[components]]
+component_name = "transformer"
+component_path = "transformer/"
+n_layers = 57
+can_shard = true
+safetensors_index_filename = "diffusion_pytorch_model.safetensors.index.json"
+
+[components.storage_size]
+in_bytes = 11901408320
+
+[[components]]
+component_name = "vae"
+component_path = "vae/"
+can_shard = false
+
+[components.storage_size]
+in_bytes = 0

resources/image_model_cards/exolabs--FLUX.1-Kontext-dev.toml

@@ -0,0 +1,49 @@
+model_id = "exolabs/FLUX.1-Kontext-dev"
+n_layers = 57
+hidden_size = 1
+supports_tensor = false
+tasks = ["ImageToImage"]
+family = "flux"
+quantization = ""
+base_model = "FLUX.1 Kontext"
+capabilities = ["image_edit"]
+
+[storage_size]
+in_bytes = 33327437952
+
+[[components]]
+component_name = "text_encoder"
+component_path = "text_encoder/"
+n_layers = 12
+can_shard = false
+
+[components.storage_size]
+in_bytes = 0
+
+[[components]]
+component_name = "text_encoder_2"
+component_path = "text_encoder_2/"
+n_layers = 24
+can_shard = false
+safetensors_index_filename = "model.safetensors.index.json"
+
+[components.storage_size]
+in_bytes = 9524621312
+
+[[components]]
+component_name = "transformer"
+component_path = "transformer/"
+n_layers = 57
+can_shard = true
+safetensors_index_filename = "diffusion_pytorch_model.safetensors.index.json"
+
+[components.storage_size]
+in_bytes = 23802816640
+
+[[components]]
+component_name = "vae"
+component_path = "vae/"
+can_shard = false
+
+[components.storage_size]
+in_bytes = 0

resources/image_model_cards/exolabs--FLUX.1-Krea-dev-4bit.toml

@@ -0,0 +1,49 @@
+model_id = "exolabs/FLUX.1-Krea-dev-4bit"
+n_layers = 57
+hidden_size = 1
+supports_tensor = false
+tasks = ["TextToImage"]
+family = "flux"
+quantization = "4bit"
+base_model = "FLUX.1 Krea"
+capabilities = ["image_gen"]
+
+[storage_size]
+in_bytes = 15475325472
+
+[[components]]
+component_name = "text_encoder"
+component_path = "text_encoder/"
+n_layers = 12
+can_shard = false
+
+[components.storage_size]
+in_bytes = 0
+
+[[components]]
+component_name = "text_encoder_2"
+component_path = "text_encoder_2/"
+n_layers = 24
+can_shard = false
+safetensors_index_filename = "model.safetensors.index.json"
+
+[components.storage_size]
+in_bytes = 9524621312
+
+[[components]]
+component_name = "transformer"
+component_path = "transformer/"
+n_layers = 57
+can_shard = true
+safetensors_index_filename = "diffusion_pytorch_model.safetensors.index.json"
+
+[components.storage_size]
+in_bytes = 5950704160
+
+[[components]]
+component_name = "vae"
+component_path = "vae/"
+can_shard = false
+
+[components.storage_size]
+in_bytes = 0

resources/image_model_cards/exolabs--FLUX.1-Krea-dev-8bit.toml

@@ -0,0 +1,49 @@
+model_id = "exolabs/FLUX.1-Krea-dev-8bit"
+n_layers = 57
+hidden_size = 1
+supports_tensor = false
+tasks = ["TextToImage"]
+family = "flux"
+quantization = "8bit"
+base_model = "FLUX.1 Krea"
+capabilities = ["image_gen"]
+
+[storage_size]
+in_bytes = 21426029632
+
+[[components]]
+component_name = "text_encoder"
+component_path = "text_encoder/"
+n_layers = 12
+can_shard = false
+
+[components.storage_size]
+in_bytes = 0
+
+[[components]]
+component_name = "text_encoder_2"
+component_path = "text_encoder_2/"
+n_layers = 24
+can_shard = false
+safetensors_index_filename = "model.safetensors.index.json"
+
+[components.storage_size]
+in_bytes = 9524621312
+
+[[components]]
+component_name = "transformer"
+component_path = "transformer/"
+n_layers = 57
+can_shard = true
+safetensors_index_filename = "diffusion_pytorch_model.safetensors.index.json"
+
+[components.storage_size]
+in_bytes = 11901408320
+
+[[components]]
+component_name = "vae"
+component_path = "vae/"
+can_shard = false
+
+[components.storage_size]
+in_bytes = 0

resources/image_model_cards/exolabs--FLUX.1-Krea-dev.toml

@@ -0,0 +1,49 @@
+model_id = "exolabs/FLUX.1-Krea-dev"
+n_layers = 57
+hidden_size = 1
+supports_tensor = false
+tasks = ["TextToImage"]
+family = "flux"
+quantization = ""
+base_model = "FLUX.1 Krea"
+capabilities = ["image_gen"]
+
+[storage_size]
+in_bytes = 33327437952
+
+[[components]]
+component_name = "text_encoder"
+component_path = "text_encoder/"
+n_layers = 12
+can_shard = false
+
+[components.storage_size]
+in_bytes = 0
+
+[[components]]
+component_name = "text_encoder_2"
+component_path = "text_encoder_2/"
+n_layers = 24
+can_shard = false
+safetensors_index_filename = "model.safetensors.index.json"
+
+[components.storage_size]
+in_bytes = 9524621312
+
+[[components]]
+component_name = "transformer"
+component_path = "transformer/"
+n_layers = 57
+can_shard = true
+safetensors_index_filename = "diffusion_pytorch_model.safetensors.index.json"
+
+[components.storage_size]
+in_bytes = 23802816640
+
+[[components]]
+component_name = "vae"
+component_path = "vae/"
+can_shard = false
+
+[components.storage_size]
+in_bytes = 0

resources/image_model_cards/exolabs--FLUX.1-dev-4bit.toml

@@ -0,0 +1,49 @@
+model_id = "exolabs/FLUX.1-dev-4bit"
+n_layers = 57
+hidden_size = 1
+supports_tensor = false
+tasks = ["TextToImage"]
+family = "flux"
+quantization = "4bit"
+base_model = "FLUX.1 Dev"
+capabilities = ["image_gen"]
+
+[storage_size]
+in_bytes = 15475325472
+
+[[components]]
+component_name = "text_encoder"
+component_path = "text_encoder/"
+n_layers = 12
+can_shard = false
+
+[components.storage_size]
+in_bytes = 0
+
+[[components]]
+component_name = "text_encoder_2"
+component_path = "text_encoder_2/"
+n_layers = 24
+can_shard = false
+safetensors_index_filename = "model.safetensors.index.json"
+
+[components.storage_size]
+in_bytes = 9524621312
+
+[[components]]
+component_name = "transformer"
+component_path = "transformer/"
+n_layers = 57
+can_shard = true
+safetensors_index_filename = "diffusion_pytorch_model.safetensors.index.json"
+
+[components.storage_size]
+in_bytes = 5950704160
+
+[[components]]
+component_name = "vae"
+component_path = "vae/"
+can_shard = false
+
+[components.storage_size]
+in_bytes = 0

resources/image_model_cards/exolabs--FLUX.1-dev-8bit.toml

@@ -0,0 +1,49 @@
+model_id = "exolabs/FLUX.1-dev-8bit"
+n_layers = 57
+hidden_size = 1
+supports_tensor = false
+tasks = ["TextToImage"]
+family = "flux"
+quantization = "8bit"
+base_model = "FLUX.1 Dev"
+capabilities = ["image_gen"]
+
+[storage_size]
+in_bytes = 21426029632
+
+[[components]]
+component_name = "text_encoder"
+component_path = "text_encoder/"
+n_layers = 12
+can_shard = false
+
+[components.storage_size]
+in_bytes = 0
+
+[[components]]
+component_name = "text_encoder_2"
+component_path = "text_encoder_2/"
+n_layers = 24
+can_shard = false
+safetensors_index_filename = "model.safetensors.index.json"
+
+[components.storage_size]
+in_bytes = 9524621312
+
+[[components]]
+component_name = "transformer"
+component_path = "transformer/"
+n_layers = 57
+can_shard = true
+safetensors_index_filename = "diffusion_pytorch_model.safetensors.index.json"
+
+[components.storage_size]
+in_bytes = 11901408320
+
+[[components]]
+component_name = "vae"
+component_path = "vae/"
+can_shard = false
+
+[components.storage_size]
+in_bytes = 0

resources/image_model_cards/exolabs--FLUX.1-dev.toml

@@ -0,0 +1,49 @@
+model_id = "exolabs/FLUX.1-dev"
+n_layers = 57
+hidden_size = 1
+supports_tensor = false
+tasks = ["TextToImage"]
+family = "flux"
+quantization = ""
+base_model = "FLUX.1 Dev"
+capabilities = ["image_gen"]
+
+[storage_size]
+in_bytes = 33327437952
+
+[[components]]
+component_name = "text_encoder"
+component_path = "text_encoder/"
+n_layers = 12
+can_shard = false
+
+[components.storage_size]
+in_bytes = 0
+
+[[components]]
+component_name = "text_encoder_2"
+component_path = "text_encoder_2/"
+n_layers = 24
+can_shard = false
+safetensors_index_filename = "model.safetensors.index.json"
+
+[components.storage_size]
+in_bytes = 9524621312
+
+[[components]]
+component_name = "transformer"
+component_path = "transformer/"
+n_layers = 57
+can_shard = true
+safetensors_index_filename = "diffusion_pytorch_model.safetensors.index.json"
+
+[components.storage_size]
+in_bytes = 23802816640
+
+[[components]]
+component_name = "vae"
+component_path = "vae/"
+can_shard = false
+
+[components.storage_size]
+in_bytes = 0

resources/image_model_cards/exolabs--FLUX.1-schnell-4bit.toml

@@ -0,0 +1,49 @@
+model_id = "exolabs/FLUX.1-schnell-4bit"
+n_layers = 57
+hidden_size = 1
+supports_tensor = false
+tasks = ["TextToImage"]
+family = "flux"
+quantization = "4bit"
+base_model = "FLUX.1 Schnell"
+capabilities = ["image_gen"]
+
+[storage_size]
+in_bytes = 15470210592
+
+[[components]]
+component_name = "text_encoder"
+component_path = "text_encoder/"
+n_layers = 12
+can_shard = false
+
+[components.storage_size]
+in_bytes = 0
+
+[[components]]
+component_name = "text_encoder_2"
+component_path = "text_encoder_2/"
+n_layers = 24
+can_shard = false
+safetensors_index_filename = "model.safetensors.index.json"
+
+[components.storage_size]
+in_bytes = 9524621312
+
+[[components]]
+component_name = "transformer"
+component_path = "transformer/"
+n_layers = 57
+can_shard = true
+safetensors_index_filename = "diffusion_pytorch_model.safetensors.index.json"
+
+[components.storage_size]
+in_bytes = 5945589280
+
+[[components]]
+component_name = "vae"
+component_path = "vae/"
+can_shard = false
+
+[components.storage_size]
+in_bytes = 0

resources/image_model_cards/exolabs--FLUX.1-schnell-8bit.toml

@@ -0,0 +1,49 @@
+model_id = "exolabs/FLUX.1-schnell-8bit"
+n_layers = 57
+hidden_size = 1
+supports_tensor = false
+tasks = ["TextToImage"]
+family = "flux"
+quantization = "8bit"
+base_model = "FLUX.1 Schnell"
+capabilities = ["image_gen"]
+
+[storage_size]
+in_bytes = 21415799872
+
+[[components]]
+component_name = "text_encoder"
+component_path = "text_encoder/"
+n_layers = 12
+can_shard = false
+
+[components.storage_size]
+in_bytes = 0
+
+[[components]]
+component_name = "text_encoder_2"
+component_path = "text_encoder_2/"
+n_layers = 24
+can_shard = false
+safetensors_index_filename = "model.safetensors.index.json"
+
+[components.storage_size]
+in_bytes = 9524621312
+
+[[components]]
+component_name = "transformer"
+component_path = "transformer/"
+n_layers = 57
+can_shard = true
+safetensors_index_filename = "diffusion_pytorch_model.safetensors.index.json"
+
+[components.storage_size]
+in_bytes = 11891178560
+
+[[components]]
+component_name = "vae"
+component_path = "vae/"
+can_shard = false
+
+[components.storage_size]
+in_bytes = 0

resources/image_model_cards/exolabs--FLUX.1-schnell.toml

@@ -0,0 +1,49 @@
+model_id = "exolabs/FLUX.1-schnell"
+n_layers = 57
+hidden_size = 1
+supports_tensor = false
+tasks = ["TextToImage"]
+family = "flux"
+quantization = ""
+base_model = "FLUX.1 Schnell"
+capabilities = ["image_gen"]
+
+[storage_size]
+in_bytes = 33306978432
+
+[[components]]
+component_name = "text_encoder"
+component_path = "text_encoder/"
+n_layers = 12
+can_shard = false
+
+[components.storage_size]
+in_bytes = 0
+
+[[components]]
+component_name = "text_encoder_2"
+component_path = "text_encoder_2/"
+n_layers = 24
+can_shard = false
+safetensors_index_filename = "model.safetensors.index.json"
+
+[components.storage_size]
+in_bytes = 9524621312
+
+[[components]]
+component_name = "transformer"
+component_path = "transformer/"
+n_layers = 57
+can_shard = true
+safetensors_index_filename = "diffusion_pytorch_model.safetensors.index.json"
+
+[components.storage_size]
+in_bytes = 23782357120
+
+[[components]]
+component_name = "vae"
+component_path = "vae/"
+can_shard = false
+
+[components.storage_size]
+in_bytes = 0

resources/image_model_cards/exolabs--Qwen-Image-4bit.toml

@@ -0,0 +1,40 @@
+model_id = "exolabs/Qwen-Image-4bit"
+n_layers = 60
+hidden_size = 1
+supports_tensor = false
+tasks = ["TextToImage"]
+uses_cfg = true
+family = "qwen-image"
+quantization = "4bit"
+base_model = "Qwen Image"
+capabilities = ["image_gen"]
+
+[storage_size]
+in_bytes = 26799533856
+
+[[components]]
+component_name = "text_encoder"
+component_path = "text_encoder/"
+n_layers = 12
+can_shard = false
+
+[components.storage_size]
+in_bytes = 16584333312
+
+[[components]]
+component_name = "transformer"
+component_path = "transformer/"
+n_layers = 60
+can_shard = true
+safetensors_index_filename = "diffusion_pytorch_model.safetensors.index.json"
+
+[components.storage_size]
+in_bytes = 10215200544
+
+[[components]]
+component_name = "vae"
+component_path = "vae/"
+can_shard = false
+
+[components.storage_size]
+in_bytes = 0

resources/image_model_cards/exolabs--Qwen-Image-8bit.toml

@@ -0,0 +1,40 @@
+model_id = "exolabs/Qwen-Image-8bit"
+n_layers = 60
+hidden_size = 1
+supports_tensor = false
+tasks = ["TextToImage"]
+uses_cfg = true
+family = "qwen-image"
+quantization = "8bit"
+base_model = "Qwen Image"
+capabilities = ["image_gen"]
+
+[storage_size]
+in_bytes = 37014734400
+
+[[components]]
+component_name = "text_encoder"
+component_path = "text_encoder/"
+n_layers = 12
+can_shard = false
+
+[components.storage_size]
+in_bytes = 16584333312
+
+[[components]]
+component_name = "transformer"
+component_path = "transformer/"
+n_layers = 60
+can_shard = true
+safetensors_index_filename = "diffusion_pytorch_model.safetensors.index.json"
+
+[components.storage_size]
+in_bytes = 20430401088
+
+[[components]]
+component_name = "vae"
+component_path = "vae/"
+can_shard = false
+
+[components.storage_size]
+in_bytes = 0

resources/image_model_cards/exolabs--Qwen-Image-Edit-2509-4bit.toml

@@ -0,0 +1,40 @@
+model_id = "exolabs/Qwen-Image-Edit-2509-4bit"
+n_layers = 60
+hidden_size = 1
+supports_tensor = false
+tasks = ["ImageToImage"]
+uses_cfg = true
+family = "qwen-image"
+quantization = "4bit"
+base_model = "Qwen Image Edit"
+capabilities = ["image_edit"]
+
+[storage_size]
+in_bytes = 26799533856
+
+[[components]]
+component_name = "text_encoder"
+component_path = "text_encoder/"
+n_layers = 12
+can_shard = false
+
+[components.storage_size]
+in_bytes = 16584333312
+
+[[components]]
+component_name = "transformer"
+component_path = "transformer/"
+n_layers = 60
+can_shard = true
+safetensors_index_filename = "diffusion_pytorch_model.safetensors.index.json"
+
+[components.storage_size]
+in_bytes = 10215200544
+
+[[components]]
+component_name = "vae"
+component_path = "vae/"
+can_shard = false
+
+[components.storage_size]
+in_bytes = 0

resources/image_model_cards/exolabs--Qwen-Image-Edit-2509-8bit.toml

@@ -0,0 +1,40 @@
+model_id = "exolabs/Qwen-Image-Edit-2509-8bit"
+n_layers = 60
+hidden_size = 1
+supports_tensor = false
+tasks = ["ImageToImage"]
+uses_cfg = true
+family = "qwen-image"
+quantization = "8bit"
+base_model = "Qwen Image Edit"
+capabilities = ["image_edit"]
+
+[storage_size]
+in_bytes = 37014734400
+
+[[components]]
+component_name = "text_encoder"
+component_path = "text_encoder/"
+n_layers = 12
+can_shard = false
+
+[components.storage_size]
+in_bytes = 16584333312
+
+[[components]]
+component_name = "transformer"
+component_path = "transformer/"
+n_layers = 60
+can_shard = true
+safetensors_index_filename = "diffusion_pytorch_model.safetensors.index.json"
+
+[components.storage_size]
+in_bytes = 20430401088
+
+[[components]]
+component_name = "vae"
+component_path = "vae/"
+can_shard = false
+
+[components.storage_size]
+in_bytes = 0

resources/image_model_cards/exolabs--Qwen-Image-Edit-2509.toml

@@ -0,0 +1,40 @@
+model_id = "exolabs/Qwen-Image-Edit-2509"
+n_layers = 60
+hidden_size = 1
+supports_tensor = false
+tasks = ["ImageToImage"]
+uses_cfg = true
+family = "qwen-image"
+quantization = ""
+base_model = "Qwen Image Edit"
+capabilities = ["image_edit"]
+
+[storage_size]
+in_bytes = 57445135488
+
+[[components]]
+component_name = "text_encoder"
+component_path = "text_encoder/"
+n_layers = 12
+can_shard = false
+
+[components.storage_size]
+in_bytes = 16584333312
+
+[[components]]
+component_name = "transformer"
+component_path = "transformer/"
+n_layers = 60
+can_shard = true
+safetensors_index_filename = "diffusion_pytorch_model.safetensors.index.json"
+
+[components.storage_size]
+in_bytes = 40860802176
+
+[[components]]
+component_name = "vae"
+component_path = "vae/"
+can_shard = false
+
+[components.storage_size]
+in_bytes = 0

resources/image_model_cards/exolabs--Qwen-Image.toml

@@ -0,0 +1,40 @@
+model_id = "exolabs/Qwen-Image"
+n_layers = 60
+hidden_size = 1
+supports_tensor = false
+tasks = ["TextToImage"]
+uses_cfg = true
+family = "qwen-image"
+quantization = ""
+base_model = "Qwen Image"
+capabilities = ["image_gen"]
+
+[storage_size]
+in_bytes = 57445135488
+
+[[components]]
+component_name = "text_encoder"
+component_path = "text_encoder/"
+n_layers = 12
+can_shard = false
+
+[components.storage_size]
+in_bytes = 16584333312
+
+[[components]]
+component_name = "transformer"
+component_path = "transformer/"
+n_layers = 60
+can_shard = true
+safetensors_index_filename = "diffusion_pytorch_model.safetensors.index.json"
+
+[components.storage_size]
+in_bytes = 40860802176
+
+[[components]]
+component_name = "vae"
+component_path = "vae/"
+can_shard = false
+
+[components.storage_size]
+in_bytes = 0

resources/inference_model_cards/mlx-community--DeepSeek-V3.1-4bit.toml

@@ -0,0 +1,12 @@
+model_id = "mlx-community/DeepSeek-V3.1-4bit"
+n_layers = 61
+hidden_size = 7168
+supports_tensor = true
+tasks = ["TextGeneration"]
+family = "deepseek"
+quantization = "4bit"
+base_model = "DeepSeek V3.1"
+capabilities = ["text", "thinking"]
+
+[storage_size]
+in_bytes = 405874409472

resources/inference_model_cards/mlx-community--DeepSeek-V3.1-8bit.toml

@@ -0,0 +1,12 @@
+model_id = "mlx-community/DeepSeek-V3.1-8bit"
+n_layers = 61
+hidden_size = 7168
+supports_tensor = true
+tasks = ["TextGeneration"]
+family = "deepseek"
+quantization = "8bit"
+base_model = "DeepSeek V3.1"
+capabilities = ["text", "thinking"]
+
+[storage_size]
+in_bytes = 765577920512

resources/inference_model_cards/mlx-community--GLM-4.5-Air-8bit.toml

@@ -0,0 +1,12 @@
+model_id = "mlx-community/GLM-4.5-Air-8bit"
+n_layers = 46
+hidden_size = 4096
+supports_tensor = false
+tasks = ["TextGeneration"]
+family = "glm"
+quantization = "8bit"
+base_model = "GLM 4.5 Air"
+capabilities = ["text", "thinking"]
+
+[storage_size]
+in_bytes = 122406567936

resources/inference_model_cards/mlx-community--GLM-4.5-Air-bf16.toml

@@ -0,0 +1,12 @@
+model_id = "mlx-community/GLM-4.5-Air-bf16"
+n_layers = 46
+hidden_size = 4096
+supports_tensor = true
+tasks = ["TextGeneration"]
+family = "glm"
+quantization = "bf16"
+base_model = "GLM 4.5 Air"
+capabilities = ["text", "thinking"]
+
+[storage_size]
+in_bytes = 229780750336

resources/inference_model_cards/mlx-community--GLM-4.7-4bit.toml

@@ -0,0 +1,12 @@
+model_id = "mlx-community/GLM-4.7-4bit"
+n_layers = 91
+hidden_size = 5120
+supports_tensor = true
+tasks = ["TextGeneration"]
+family = "glm"
+quantization = "4bit"
+base_model = "GLM 4.7"
+capabilities = ["text", "thinking"]
+
+[storage_size]
+in_bytes = 198556925568

resources/inference_model_cards/mlx-community--GLM-4.7-6bit.toml

@@ -0,0 +1,12 @@
+model_id = "mlx-community/GLM-4.7-6bit"
+n_layers = 91
+hidden_size = 5120
+supports_tensor = true
+tasks = ["TextGeneration"]
+family = "glm"
+quantization = "6bit"
+base_model = "GLM 4.7"
+capabilities = ["text", "thinking"]
+
+[storage_size]
+in_bytes = 286737579648