Compare commits

..

5 Commits

Author SHA1 Message Date
rltakashige ed4ee8010b Merge branch 'main' into jaccl-build-fix 2026-02-10 12:29:04 +00:00
Evan 103cbdee58 shfmt ignore 2026-02-06 17:08:26 +00:00
Evan dbcc829625 sdk version? 2026-02-06 16:58:18 +00:00
Evan 30b384e2e6 vendor the apple sdk nix package 2026-02-06 16:40:10 +00:00
Evan 6675feed71 enable MLX_BUILD_CPU in nix built mlx 2026-02-06 16:14:04 +00:00
186 changed files with 5775 additions and 10117 deletions
+1 -7
View File
@@ -396,7 +396,7 @@ jobs:
path: output/EXO-${{ env.RELEASE_VERSION }}.dmg
- name: Upload to S3
if: env.SPARKLE_S3_BUCKET != ''
if: env.SPARKLE_S3_BUCKET != '' && github.ref_type == 'tag'
env:
AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_ID }}
AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
@@ -412,12 +412,6 @@ jobs:
PREFIX="${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"
+27
View File
@@ -8,6 +8,33 @@ 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 }}
+1 -1
View File
@@ -200,7 +200,7 @@ class Module(dict):
) -> mx.MX_ARRAY_TREE: # -> dict[Any, Any | dict[Any, Any | dict[Any, Any] | list[Any]] | dict[Any, Any] | list[Any]]:
"""Return the submodules that do not contain other modules."""
def update(self, parameters: dict[str, Any], strict: bool = ...) -> Module:
def update(self, parameters: dict, strict: bool = ...) -> Module:
"""Replace the parameters of this Module with the provided ones in the
dict of dicts and lists.
+8 -11
View File
@@ -7,10 +7,7 @@ from typing import Any, Callable, Dict, List, Optional, Tuple, Union
from mlx.core import MX_ARRAY_TREE
def tree_map(
fn: Callable[..., Any],
tree: Any,
*rest: Any,
is_leaf: Callable[..., bool] | None = ...,
fn: Callable, tree: Any, *rest: Any, is_leaf: Optional[Callable] = ...
) -> Any:
"""Applies ``fn`` to the leaves of the Python tree ``tree`` and
returns a new collection with the results.
@@ -47,11 +44,11 @@ def tree_map(
"""
def tree_map_with_path(
fn: Callable[..., Any],
fn: Callable,
tree: Any,
*rest: Any,
is_leaf: Callable[..., bool] | None = ...,
path: str | None = ...,
is_leaf: Optional[Callable] = ...,
path: Optional[Any] = ...,
) -> Any:
"""Applies ``fn`` to the path and leaves of the Python tree ``tree`` and
returns a new collection with the results.
@@ -83,9 +80,9 @@ def tree_map_with_path(
def tree_flatten(
tree: Any,
prefix: str = ...,
is_leaf: Callable[..., bool] | None = ...,
destination: list[tuple[str, Any]] | dict[str, Any] | None = ...,
) -> list[tuple[str, Any]] | dict[str, Any]:
is_leaf: Optional[Callable] = ...,
destination: Optional[Union[List[Tuple[str, Any]], Dict[str, Any]]] = ...,
) -> Union[List[Tuple[str, Any]], Dict[str, Any]]:
"""Flattens a Python tree to a list of key, value tuples.
The keys are using the dot notation to define trees of arbitrary depth and
@@ -121,7 +118,7 @@ def tree_flatten(
the Python tree.
"""
def tree_unflatten(tree: list[tuple[str, Any]] | dict[str, Any]) -> Any:
def tree_unflatten(tree: Union[List[Tuple[str, Any]], Dict[str, Any]]) -> Any:
"""Recreate a Python tree from its flat representation.
.. code-block:: python
@@ -1,46 +0,0 @@
"""Type stubs for mlx_lm.models.glm_moe_dsa"""
from dataclasses import dataclass
from typing import Any, Dict, Optional
from .base import BaseModelArgs
from .deepseek_v32 import Model as DSV32Model
@dataclass
class ModelArgs(BaseModelArgs):
model_type: str
vocab_size: int
hidden_size: int
index_head_dim: int
index_n_heads: int
index_topk: int
intermediate_size: int
moe_intermediate_size: int
num_hidden_layers: int
num_attention_heads: int
num_key_value_heads: int
n_shared_experts: Optional[int]
n_routed_experts: Optional[int]
routed_scaling_factor: float
kv_lora_rank: int
q_lora_rank: int
qk_rope_head_dim: int
v_head_dim: int
qk_nope_head_dim: int
topk_method: str
scoring_func: str
norm_topk_prob: bool
n_group: int
topk_group: int
num_experts_per_tok: int
moe_layer_freq: int
first_k_dense_replace: int
max_position_embeddings: int
rms_norm_eps: float
rope_parameters: Dict[str, Any]
attention_bias: bool
rope_scaling: Dict[str, Any] | None
rope_theta: float | None
class Model(DSV32Model):
def __init__(self, config: ModelArgs) -> None: ...
-151
View File
@@ -1,151 +0,0 @@
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: ...
-75
View File
@@ -119,78 +119,3 @@ 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.
Generated
+225 -11
View File
@@ -141,6 +141,12 @@ version = "0.3.9"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "76a2e8124351fda1ef8aaaa3bbd7ebbcb486bbcd4225aca0aa0d84bb2db8fecb"
[[package]]
name = "arrayvec"
version = "0.7.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7c02d123df017efcdfbd739ef81735b36c5ba83ec3c59c80a9d7ecc718f92e50"
[[package]]
name = "asn1-rs"
version = "0.7.1"
@@ -298,6 +304,19 @@ version = "1.8.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "55248b47b0caf0546f7988906588779981c43bb1bc9d0c44087278f80cdb44ba"
[[package]]
name = "bigdecimal"
version = "0.4.9"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "560f42649de9fa436b73517378a147ec21f6c997a546581df4b4b31677828934"
dependencies = [
"autocfg",
"libm",
"num-bigint",
"num-integer",
"num-traits",
]
[[package]]
name = "bimap"
version = "0.6.3"
@@ -334,6 +353,31 @@ 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"
@@ -497,6 +541,15 @@ version = "0.4.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "2f421161cb492475f1661ddc9815a745a1c894592070661180fdec3d4872e9c3"
[[package]]
name = "convert_case"
version = "0.10.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "633458d4ef8c78b72454de2d54fd6ab2e60f9e02be22f3c6104cdc8a4e0fceb9"
dependencies = [
"unicode-segmentation",
]
[[package]]
name = "core-foundation"
version = "0.9.4"
@@ -647,6 +700,41 @@ 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"
@@ -718,6 +806,29 @@ dependencies = [
"powerfmt",
]
[[package]]
name = "derive_more"
version = "2.1.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "10b768e943bed7bf2cab53df09f4bc34bfd217cdb57d971e769874c9a6710618"
dependencies = [
"derive_more-impl",
]
[[package]]
name = "derive_more-impl"
version = "2.1.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "6d286bfdaf75e988b4a78e013ecd79c581e06399ab53fbacd2d916c2f904f30b"
dependencies = [
"convert_case",
"proc-macro2",
"quote",
"rustc_version",
"syn 2.0.111",
"unicode-xid",
]
[[package]]
name = "digest"
version = "0.10.7"
@@ -888,17 +999,22 @@ name = "exo_pyo3_bindings"
version = "0.0.1"
dependencies = [
"delegate",
"derive_more",
"env_logger",
"extend",
"futures-lite",
"futures",
"impl-trait-for-tuples",
"libp2p",
"log",
"networking",
"once_cell",
"pin-project",
"pyo3",
"pyo3-async-runtimes",
"pyo3-log",
"pyo3-stub-gen",
"thiserror 2.0.17",
"thread_local",
"tokio",
"util",
]
@@ -914,12 +1030,6 @@ dependencies = [
"syn 2.0.111",
]
[[package]]
name = "fastrand"
version = "2.3.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "37909eebbb50d72f9059c3b6d82c0463f2ff062c9e95845c43a6c9c0355411be"
[[package]]
name = "ff"
version = "0.13.1"
@@ -1028,10 +1138,7 @@ version = "2.6.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "f78e10609fe0e0b3f4157ffab1876319b5b0db102a2c60dc4626306dc46b44ad"
dependencies = [
"fastrand",
"futures-core",
"futures-io",
"parking",
"pin-project-lite",
]
@@ -1518,6 +1625,12 @@ 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"
@@ -1593,6 +1706,17 @@ dependencies = [
"xmltree",
]
[[package]]
name = "impl-trait-for-tuples"
version = "0.2.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a0eb5a3343abf848c0984fe4604b2b105da9539376e24fc0a3b0007411ae4fd9"
dependencies = [
"proc-macro2",
"quote",
"syn 2.0.111",
]
[[package]]
name = "indexmap"
version = "2.12.1"
@@ -1621,6 +1745,15 @@ 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"
@@ -1771,6 +1904,12 @@ version = "0.2.178"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "37c93d8daa9d8a012fd8ab92f088405fb202ea0b6ab73ee2482ae66af4f42091"
[[package]]
name = "libm"
version = "0.2.15"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "f9fbbcab51052fe104eb5e5d351cf728d30a5be1fe14d9be8a3b097481fb97de"
[[package]]
name = "libp2p"
version = "0.56.0"
@@ -2760,13 +2899,16 @@ name = "networking"
version = "0.0.1"
dependencies = [
"delegate",
"derive_more",
"either",
"extend",
"futures-lite",
"futures",
"futures-timer",
"impl-trait-for-tuples",
"keccak-const",
"libp2p",
"log",
"thiserror 2.0.17",
"tokio",
"tracing-subscriber",
"util",
@@ -2851,6 +2993,17 @@ dependencies = [
"num-traits",
]
[[package]]
name = "num-rational"
version = "0.4.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "f83d14da390562dca69fc84082e73e548e1ad308d24accdedd2720017cb37824"
dependencies = [
"num-bigint",
"num-integer",
"num-traits",
]
[[package]]
name = "num-traits"
version = "0.2.19"
@@ -3154,6 +3307,16 @@ 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"
@@ -3201,14 +3364,28 @@ version = "0.27.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ab53c047fcd1a1d2a8820fe84f05d6be69e9526be40cb03b73f86b6b03e6d87d"
dependencies = [
"bigdecimal",
"either",
"hashbrown 0.16.1",
"indexmap",
"indoc",
"inventory",
"libc",
"lock_api",
"memoffset",
"num-bigint",
"num-complex",
"num-rational",
"num-traits",
"once_cell",
"ordered-float",
"parking_lot",
"portable-atomic",
"pyo3-build-config",
"pyo3-ffi",
"pyo3-macros",
"rust_decimal",
"smallvec",
"unindent",
]
@@ -3563,6 +3740,12 @@ 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"
@@ -3649,6 +3832,16 @@ dependencies = [
"tokio",
]
[[package]]
name = "rust_decimal"
version = "1.39.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "35affe401787a9bd846712274d97654355d21b2a2c092a3139aabe31e9022282"
dependencies = [
"arrayvec",
"num-traits",
]
[[package]]
name = "rustc-hash"
version = "1.1.0"
@@ -4513,12 +4706,24 @@ version = "1.0.22"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9312f7c4f6ff9069b165498234ce8be658059c6728633667c526e27dc2cf1df5"
[[package]]
name = "unicode-segmentation"
version = "1.12.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "f6ccf251212114b54433ec949fd6a7841275f9ada20dddd2f29e9ceea4501493"
[[package]]
name = "unicode-width"
version = "0.2.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b4ac048d71ede7ee76d585517add45da530660ef4390e49b098733c6e897f254"
[[package]]
name = "unicode-xid"
version = "0.2.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ebc1c04c71510c7f702b52b7c350734c9ff1295c464a03335b00bb84fc54f853"
[[package]]
name = "unicode_names2"
version = "1.3.0"
@@ -4602,6 +4807,15 @@ 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"
+30 -1
View File
@@ -26,20 +26,49 @@ opt-level = 3
networking = { path = "rust/networking" }
util = { path = "rust/util" }
# Proc-macro authoring tools
syn = "2.0"
quote = "1.0"
proc-macro2 = "1.0"
darling = "0.20"
# Macro dependecies
extend = "1.2"
delegate = "0.13"
impl-trait-for-tuples = "0.2"
clap = "4.5"
derive_more = { version = "2.0.1", features = ["display"] }
pin-project = "1"
# Utility dependencies
itertools = "0.14"
thiserror = "2"
internment = "0.8"
recursion = "0.5"
regex = "1.11"
once_cell = "1.21"
thread_local = "1.1"
bon = "3.4"
generativity = "1.1"
anyhow = "1.0"
keccak-const = "0.2"
# Functional generics/lenses frameworks
frunk_core = "0.4"
frunk = "0.4"
frunk_utils = "0.2"
frunk-enum-core = "0.3"
# Async dependencies
tokio = "1.46"
futures-lite = "2.6.1"
futures = "0.3"
futures-util = "0.3"
futures-timer = "3.0"
# Data structures
either = "1.15"
ordered-float = "5.0"
ahash = "0.8"
# Tracing/logging
log = "0.4"
+11 -11
View File
@@ -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.
[X] no mx_barrier in genreate.py mlx_generate at the end.
[] no mx_barrier in genreate.py mlx_generate at the end.
[] cache assertion not needed in auto_parallel.py PipelineLastLayer.
[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.
[] 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.
[] Dropped prefill/decode code in auto_parallel.py and utils_mlx.py.
[X] KV_CACHE_BITS should be None to disable quantized KV cache.
[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.
[] 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] We put cache limit back in utils_mlx.py.
[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.)
[] 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.)
[] 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).
+2 -16
View File
@@ -72,30 +72,16 @@ There are two ways to run exo:
### Run from Source (macOS)
If you have [Nix](https://nixos.org/) installed, you can skip most of the steps below and run exo directly:
```bash
nix run .#exo
```
**Note:** To accept the Cachix binary cache (and avoid the Xcode Metal ToolChain), add to `/etc/nix/nix.conf`:
```
trusted-users = root (or your username)
experimental-features = nix-command flakes
```
Then restart the Nix daemon: `sudo launchctl kickstart -k system/org.nixos.nix-daemon`
**Prerequisites:**
- [Xcode](https://developer.apple.com/xcode/) (provides the Metal ToolChain required for MLX compilation)
- [brew](https://github.com/Homebrew/brew) (for simple package management on macOS)
```bash
/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)"
```
- [uv](https://github.com/astral-sh/uv) (for Python dependency management)
- [macmon](https://github.com/vladkens/macmon) (for hardware monitoring on Apple Silicon)
- [node](https://github.com/nodejs/node) (for building the dashboard)
```bash
brew install uv macmon node
```
+14
View File
@@ -1,14 +1,28 @@
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:
+31 -33
View File
@@ -563,45 +563,21 @@ struct ContentView: View {
}
private var rdmaStatusView: some View {
let rdmaStatuses = stateService.latestSnapshot?.nodeRdmaCtl ?? [:]
let localNodeId = stateService.localNodeId
let nodeProfiles = stateService.latestSnapshot?.nodeProfiles ?? [:]
let localDevices = networkStatusService.status.localRdmaDevices
let localPorts = networkStatusService.status.localRdmaActivePorts
let rdma = networkStatusService.status.rdmaStatus
return VStack(alignment: .leading, spacing: 1) {
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: ", "))")
Text("RDMA: \(rdmaStatusText(rdma))")
.font(.caption2)
.foregroundColor(rdmaStatusColor(rdma))
if !rdma.devices.isEmpty {
Text(" Devices: \(rdma.devices.joined(separator: ", "))")
.font(.caption2)
.foregroundColor(.secondary)
}
if !localPorts.isEmpty {
Text(" Local Active Ports:")
if !rdma.activePorts.isEmpty {
Text(" Active Ports:")
.font(.caption2)
.foregroundColor(.secondary)
ForEach(localPorts, id: \.device) { port in
ForEach(rdma.activePorts, id: \.device) { port in
Text(" \(port.device) port \(port.port): \(port.state)")
.font(.caption2)
.foregroundColor(.green)
@@ -610,6 +586,28 @@ 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 {
+4 -38
View File
@@ -28,10 +28,6 @@ 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?
@@ -82,11 +78,7 @@ final class ExoProcessController: ObservableObject {
let child = Process()
child.executableURL = executableURL
let exoHomeURL = Self.exoDirectoryURL
try? FileManager.default.createDirectory(
at: exoHomeURL, withIntermediateDirectories: true
)
child.currentDirectoryURL = exoHomeURL
child.currentDirectoryURL = runtimeURL
child.environment = makeEnvironment(for: runtimeURL)
child.standardOutput = FileHandle.nullDevice
@@ -126,37 +118,11 @@ final class ExoProcessController: ObservableObject {
return
}
process.terminationHandler = nil
status = .stopped
guard process.isRunning else {
self.process = nil
return
if process.isRunning {
process.terminate()
}
let proc = process
self.process = nil
Task.detached {
proc.interrupt()
for _ in 0..<50 {
if !proc.isRunning { return }
try? await Task.sleep(nanoseconds: 100_000_000)
}
if proc.isRunning {
proc.terminate()
}
for _ in 0..<30 {
if !proc.isRunning { return }
try? await Task.sleep(nanoseconds: 100_000_000)
}
if proc.isRunning {
kill(proc.processIdentifier, SIGKILL)
}
}
status = .stopped
}
func restart() {
-10
View File
@@ -15,7 +15,6 @@ 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] {
@@ -66,10 +65,6 @@ 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 {
@@ -83,7 +78,6 @@ struct ClusterState: Decodable {
case nodeMemory
case nodeSystem
case nodeThunderboltBridge
case nodeRdmaCtl
}
}
@@ -165,10 +159,6 @@ struct ThunderboltBridgeStatus: Decodable {
let serviceName: String?
}
struct NodeRdmaCtlStatus: Decodable {
let enabled: Bool
}
struct MemoryInfo: Decodable {
let ramTotal: MemoryValue?
let ramAvailable: MemoryValue?
+14 -46
View File
@@ -44,12 +44,16 @@ struct BugReportService {
let dayPrefix = Self.dayPrefixString(now)
let prefix = "reports/\(dayPrefix)/\(timestamp)/"
let logFiles = readAllLogs()
let logData = readLog()
let ifconfigText = try await captureIfconfig()
let hostName = Host.current().localizedName ?? "unknown"
let debugInfo = readDebugInfo()
let stateData = try await fetch(url: baseURL.appendingPathComponent("state"))
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
// Extract cluster TB bridge status from exo state
let clusterTbBridgeStatus = extractClusterTbBridgeStatus(from: stateData)
@@ -63,19 +67,12 @@ struct BugReportService {
clusterTbBridgeStatus: clusterTbBridgeStatus
)
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: [
let uploads: [(path: String, data: Data?)] = [
("\(prefix)exo.log", logData),
("\(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 }
@@ -152,40 +149,11 @@ struct BugReportService {
return decoded.urls
}
private func readAllLogs() -> [(path: String, data: Data)] {
let dir = URL(fileURLWithPath: NSHomeDirectory())
private func readLog() -> Data? {
let logURL = URL(fileURLWithPath: NSHomeDirectory())
.appendingPathComponent(".exo")
.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
.appendingPathComponent("exo.log")
return try? Data(contentsOf: logURL)
}
private func captureIfconfig() async throws -> String {
@@ -35,18 +35,28 @@ struct NetworkStatus: Equatable {
let thunderboltBridgeState: ThunderboltState?
let bridgeInactive: Bool?
let interfaceStatuses: [InterfaceIpStatus]
let localRdmaDevices: [String]
let localRdmaActivePorts: [RDMAPort]
let rdmaStatus: RDMAStatus
static let empty = NetworkStatus(
thunderboltBridgeState: nil,
bridgeInactive: nil,
interfaceStatuses: [],
localRdmaDevices: [],
localRdmaActivePorts: []
rdmaStatus: .empty
)
}
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
@@ -70,11 +80,31 @@ private struct NetworkStatusFetcher {
thunderboltBridgeState: readThunderboltBridgeState(),
bridgeInactive: readBridgeInactive(),
interfaceStatuses: readInterfaceStatuses(),
localRdmaDevices: readRDMADevices(),
localRdmaActivePorts: readRDMAActivePorts()
rdmaStatus: readRDMAStatus()
)
}
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 [] }
-7
View File
@@ -1,7 +0,0 @@
# Canary benchmark manifest
#
# Lists the suite files to include. Each file defines benchmarks
# with shared constraints, topology, and default args.
include = [
"single-m3-ultra.toml",
]
File diff suppressed because it is too large Load Diff
+274 -46
View File
@@ -1,45 +1,21 @@
# type: ignore
#!/usr/bin/env python3
"""Tool-calling eval for exo's OpenAI-compatible API.
Tests whether models correctly:
- Trigger tool calls when appropriate
- Return valid JSON arguments matching function schemas
- Handle multi-turn tool use (call -> result -> final answer)
- Avoid calling tools when unnecessary
Start exo with a model first, then run:
uv run python tool_call_eval.py --model <model-id>
uv run python tool_call_eval.py --model <model-id> --host 10.0.0.5 --port 52415
uv run python tool_call_eval.py --model <model-id> --repeat 3
uv run python tool_call_eval.py --model <model-id> --scenarios weather_simple calculator_multi_turn
"""
# pyright: reportAny=false, reportUnknownMemberType=false, reportUnknownVariableType=false, reportUnknownArgumentType=false
from __future__ import annotations
import argparse
import contextlib
import http.client
import itertools
import json
import os
import sys
import time
from collections.abc import Callable
from pathlib import Path
from statistics import mean
from typing import Any
from urllib.parse import urlencode
from harness import (
ExoClient,
ExoHttpError,
add_common_instance_args,
instance_id_from_instance,
nodes_used_in_instance,
resolve_model_short_id,
run_planning_phase,
settle_and_fetch_placements,
wait_for_instance_gone,
wait_for_instance_ready,
)
from loguru import logger
from transformers import AutoTokenizer
@@ -122,6 +98,154 @@ def load_tokenizer_for_bench(model_id: str) -> Any:
return AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
class ExoHttpError(RuntimeError):
def __init__(self, status: int, reason: str, body_preview: str):
super().__init__(f"HTTP {status} {reason}: {body_preview}")
self.status = status
class ExoClient:
def __init__(self, host: str, port: int, timeout_s: float = 7200.0):
self.host = host
self.port = port
self.timeout_s = timeout_s
def request_json(
self,
method: str,
path: str,
params: dict[str, Any] | None = None,
body: dict[str, Any] | None = None,
headers: dict[str, str] | None = None,
) -> Any:
if not path.startswith("/"):
path = "/" + path
if params:
path = path + "?" + urlencode(params)
conn = http.client.HTTPConnection(self.host, self.port, timeout=self.timeout_s)
try:
payload: bytes | None = None
hdrs: dict[str, str] = {"Accept": "application/json"}
if body is not None:
payload = json.dumps(body).encode("utf-8")
hdrs["Content-Type"] = "application/json"
if headers:
hdrs.update(headers)
conn.request(method.upper(), path, body=payload, headers=hdrs)
resp = conn.getresponse()
raw = resp.read()
text = raw.decode("utf-8", errors="replace") if raw else ""
if resp.status >= 400:
raise ExoHttpError(resp.status, resp.reason, text[:300])
if not text:
return None
return json.loads(text)
finally:
conn.close()
def post_bench_chat_completions(self, payload: dict[str, Any]) -> dict[str, Any]:
return self.request_json("POST", "/bench/chat/completions", body=payload)
def unwrap_instance(instance: dict[str, Any]) -> dict[str, Any]:
if len(instance) != 1:
raise KeyError(f"Expected 1 key, got keys={list(instance.keys())}")
tag = next(iter(instance))
inner = instance[tag]
if not isinstance(inner, dict):
raise TypeError(f"payload for {tag} must be dict, got {type(inner)}")
return inner
def instance_id_from_instance(instance: dict[str, Any]) -> str:
inner = unwrap_instance(instance)
return str(inner["instanceId"])
def nodes_used_in_instance(instance: dict[str, Any]) -> int:
inner = unwrap_instance(instance)
return len(inner["shardAssignments"]["nodeToRunner"])
def runner_ids_from_instance(instance: dict[str, Any]) -> list[str]:
inner = unwrap_instance(instance)
runner_to_shard = inner["shardAssignments"]["runnerToShard"]
return list(runner_to_shard.keys())
def runner_ready(runner: dict[str, Any]) -> bool:
return "RunnerReady" in runner
def runner_failed(runner: dict[str, Any]) -> bool:
return "RunnerFailed" in runner
def get_runner_failed_message(runner: dict[str, Any]) -> str | None:
if "RunnerFailed" in runner:
return runner["RunnerFailed"].get("errorMessage")
return None
def wait_for_instance_ready(
client: ExoClient, instance_id: str, timeout: float = 24000.0
) -> None:
start_time = time.time()
instance_existed = False
while time.time() - start_time < timeout:
state = client.request_json("GET", "/state")
instances = state.get("instances", {})
if instance_id not in instances:
if instance_existed:
# Instance was deleted after being created - likely due to runner failure
raise RuntimeError(
f"Instance {instance_id} was deleted (runner may have failed)"
)
time.sleep(0.1)
continue
instance_existed = True
instance = instances[instance_id]
runner_ids = runner_ids_from_instance(instance)
runners = state.get("runners", {})
# Check for failed runners first
for rid in runner_ids:
runner = runners.get(rid, {})
if runner_failed(runner):
error_msg = get_runner_failed_message(runner) or "Unknown error"
raise RuntimeError(f"Runner {rid} failed: {error_msg}")
if all(runner_ready(runners.get(rid, {})) for rid in runner_ids):
return
time.sleep(0.1)
raise TimeoutError(f"Instance {instance_id} did not become ready within {timeout=}")
def wait_for_instance_gone(
client: ExoClient, instance_id: str, timeout: float = 3.0
) -> None:
start_time = time.time()
while time.time() - start_time < timeout:
try:
client.request_json("GET", f"/instance/{instance_id}")
time.sleep(0.4)
except ExoHttpError as e:
if e.status == 404:
return
raise TimeoutError(f"Instance {instance_id} did not get deleted within {timeout=}")
def format_peak_memory(b: float) -> str:
for unit in ["B", "KB", "MB", "GB", "TB"]:
if b < 1024.0:
@@ -140,6 +264,39 @@ def parse_int_list(values: list[str]) -> list[int]:
return items
def resolve_model_short_id(client: ExoClient, model_arg: str) -> tuple[str, str]:
models = client.request_json("GET", "/models") or {}
data = models.get("data") or []
for m in data:
if m.get("name").lower() == model_arg.lower():
short_id = str(m["name"])
full_id = str(m.get("hugging_face_id") or m["name"])
return short_id, full_id
for m in data:
if m.get("hugging_face_id") == model_arg:
short_id = str(m["name"])
full_id = str(m["hugging_face_id"])
return short_id, full_id
raise ValueError(f"Model not found in /models: {model_arg}")
def placement_filter(instance_meta: str, wanted: str) -> bool:
s = (instance_meta or "").lower()
if wanted == "both":
return ("ring" in s) or ("jaccl" in s)
return wanted in s
def sharding_filter(sharding: str, wanted: str) -> bool:
s = (sharding or "").lower()
if wanted == "both":
return ("pipeline" in s) or ("tensor" in s)
return wanted in s
def run_one_completion(
client: ExoClient, model_id: str, pp_hint: int, tg: int, prompt_sizer: PromptSizer
) -> tuple[dict[str, Any], int]:
@@ -236,7 +393,11 @@ def main() -> int:
prog="exo-bench",
description="Benchmark exo model throughput across placement previews.",
)
add_common_instance_args(ap)
ap.add_argument("--host", default=os.environ.get("EXO_HOST", "localhost"))
ap.add_argument(
"--port", type=int, default=int(os.environ.get("EXO_PORT", "52415"))
)
ap.add_argument("--model", required=True, help="Model short id or huggingface id")
ap.add_argument(
"--pp",
nargs="+",
@@ -249,6 +410,34 @@ def main() -> int:
required=True,
help="Generation lengths (ints). Accepts commas.",
)
ap.add_argument(
"--max-nodes",
type=int,
default=4,
help="Only consider placements using <= this many nodes.",
)
ap.add_argument(
"--min-nodes",
type=int,
default=1,
help="Only consider placements using >= this many nodes.",
)
ap.add_argument(
"--instance-meta", choices=["ring", "jaccl", "both"], default="both"
)
ap.add_argument(
"--sharding", choices=["pipeline", "tensor", "both"], default="both"
)
ap.add_argument(
"--skip-pipeline-jaccl",
action="store_true",
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."
)
@@ -258,6 +447,9 @@ def main() -> int:
default=0,
help="Warmup runs per placement (uses first pp/tg).",
)
ap.add_argument(
"--timeout", type=float, default=7200.0, help="HTTP timeout (seconds)."
)
ap.add_argument(
"--json-out",
default="bench/results.json",
@@ -295,6 +487,11 @@ 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")
@@ -306,9 +503,54 @@ def main() -> int:
logger.error("[exo-bench] tokenizer usable but prompt sizing failed")
raise
selected = settle_and_fetch_placements(
client, full_model_id, args, settle_timeout=args.settle_timeout
)
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)
if not selected:
logger.error("No valid placements matched your filters.")
@@ -333,20 +575,6 @@ def main() -> int:
if args.dry_run:
return 0
settle_deadline = (
time.monotonic() + args.settle_timeout if args.settle_timeout > 0 else None
)
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:
-477
View File
@@ -1,477 +0,0 @@
# type: ignore
from __future__ import annotations
import argparse
import http.client
import json
import os
import time
from typing import Any
from urllib.parse import urlencode
from loguru import logger
_SETTLE_INITIAL_BACKOFF_S = 1.0
_SETTLE_MAX_BACKOFF_S = 60.0
_SETTLE_BACKOFF_MULTIPLIER = 2.0
class ExoHttpError(RuntimeError):
def __init__(self, status: int, reason: str, body_preview: str):
super().__init__(f"HTTP {status} {reason}: {body_preview}")
self.status = status
class ExoClient:
def __init__(self, host: str, port: int, timeout_s: float = 7200.0):
self.host = host
self.port = port
self.timeout_s = timeout_s
def request_json(
self,
method: str,
path: str,
params: dict[str, Any] | None = None,
body: dict[str, Any] | None = None,
headers: dict[str, str] | None = None,
) -> Any:
if not path.startswith("/"):
path = "/" + path
if params:
path = path + "?" + urlencode(params)
conn = http.client.HTTPConnection(self.host, self.port, timeout=self.timeout_s)
try:
payload: bytes | None = None
hdrs: dict[str, str] = {"Accept": "application/json"}
if body is not None:
payload = json.dumps(body).encode("utf-8")
hdrs["Content-Type"] = "application/json"
if headers:
hdrs.update(headers)
conn.request(method.upper(), path, body=payload, headers=hdrs)
resp = conn.getresponse()
raw = resp.read()
text = raw.decode("utf-8", errors="replace") if raw else ""
if resp.status >= 400:
raise ExoHttpError(resp.status, resp.reason, text[:300])
if not text:
return None
return json.loads(text)
finally:
conn.close()
def post_bench_chat_completions(self, payload: dict[str, Any]) -> dict[str, Any]:
return self.request_json("POST", "/bench/chat/completions", body=payload)
def unwrap_instance(instance: dict[str, Any]) -> dict[str, Any]:
if len(instance) != 1:
raise KeyError(f"Expected 1 key, got keys={list(instance.keys())}")
tag = next(iter(instance))
inner = instance[tag]
if not isinstance(inner, dict):
raise TypeError(f"payload for {tag} must be dict, got {type(inner)}")
return inner
def instance_id_from_instance(instance: dict[str, Any]) -> str:
inner = unwrap_instance(instance)
return str(inner["instanceId"])
def nodes_used_in_instance(instance: dict[str, Any]) -> int:
inner = unwrap_instance(instance)
return len(inner["shardAssignments"]["nodeToRunner"])
def runner_ids_from_instance(instance: dict[str, Any]) -> list[str]:
inner = unwrap_instance(instance)
runner_to_shard = inner["shardAssignments"]["runnerToShard"]
return list(runner_to_shard.keys())
def runner_ready(runner: dict[str, Any]) -> bool:
return "RunnerReady" in runner
def runner_failed(runner: dict[str, Any]) -> bool:
return "RunnerFailed" in runner
def get_runner_failed_message(runner: dict[str, Any]) -> str | None:
if "RunnerFailed" in runner:
return runner["RunnerFailed"].get("errorMessage")
return None
def wait_for_instance_ready(
client: ExoClient, instance_id: str, timeout: float = 24000.0
) -> None:
start_time = time.time()
instance_existed = False
while time.time() - start_time < timeout:
state = client.request_json("GET", "/state")
instances = state.get("instances", {})
if instance_id not in instances:
if instance_existed:
# Instance was deleted after being created - likely due to runner failure
raise RuntimeError(
f"Instance {instance_id} was deleted (runner may have failed)"
)
time.sleep(0.1)
continue
instance_existed = True
instance = instances[instance_id]
runner_ids = runner_ids_from_instance(instance)
runners = state.get("runners", {})
# Check for failed runners first
for rid in runner_ids:
runner = runners.get(rid, {})
if runner_failed(runner):
error_msg = get_runner_failed_message(runner) or "Unknown error"
raise RuntimeError(f"Runner {rid} failed: {error_msg}")
if all(runner_ready(runners.get(rid, {})) for rid in runner_ids):
return
time.sleep(0.1)
raise TimeoutError(f"Instance {instance_id} did not become ready within {timeout=}")
def wait_for_instance_gone(
client: ExoClient, instance_id: str, timeout: float = 3.0
) -> None:
start_time = time.time()
while time.time() - start_time < timeout:
try:
client.request_json("GET", f"/instance/{instance_id}")
time.sleep(0.4)
except ExoHttpError as e:
if e.status == 404:
return
raise
raise TimeoutError(f"Instance {instance_id} did not get deleted within {timeout=}")
def resolve_model_short_id(client: ExoClient, model_arg: str) -> tuple[str, str]:
models = client.request_json("GET", "/models") or {}
data = models.get("data") or []
for m in data:
if (m.get("name") or "").lower() == model_arg.lower():
short_id = str(m["name"])
full_id = str(m.get("hugging_face_id") or m["name"])
return short_id, full_id
for m in data:
if m.get("hugging_face_id") == model_arg:
short_id = str(m["name"])
full_id = str(m["hugging_face_id"])
return short_id, full_id
raise ValueError(f"Model not found in /models: {model_arg}")
def placement_filter(instance_meta: str, wanted: str) -> bool:
s = (instance_meta or "").lower()
if wanted == "both":
return ("ring" in s) or ("jaccl" in s)
return wanted in s
def sharding_filter(sharding: str, wanted: str) -> bool:
s = (sharding or "").lower()
if wanted == "both":
return ("pipeline" in s) or ("tensor" in s)
return wanted in s
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 settle_and_fetch_placements(
client: ExoClient,
full_model_id: str,
args: argparse.Namespace,
settle_timeout: float = 0,
) -> list[dict[str, Any]]:
selected = fetch_and_filter_placements(client, full_model_id, args)
if not selected and settle_timeout > 0:
backoff = _SETTLE_INITIAL_BACKOFF_S
deadline = time.monotonic() + settle_timeout
while not selected and time.monotonic() < deadline:
remaining = 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)..."
)
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)
return selected
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 add_common_instance_args(ap: argparse.ArgumentParser) -> None:
ap.add_argument("--host", default=os.environ.get("EXO_HOST", "localhost"))
ap.add_argument(
"--port", type=int, default=int(os.environ.get("EXO_PORT", "52415"))
)
ap.add_argument("--model", required=True, help="Model short id or huggingface id")
ap.add_argument(
"--max-nodes",
type=int,
default=4,
help="Only consider placements using <= this many nodes.",
)
ap.add_argument(
"--min-nodes",
type=int,
default=1,
help="Only consider placements using >= this many nodes.",
)
ap.add_argument(
"--instance-meta", choices=["ring", "jaccl", "both"], default="both"
)
ap.add_argument(
"--sharding", choices=["pipeline", "tensor", "both"], default="both"
)
ap.add_argument(
"--skip-pipeline-jaccl",
action="store_true",
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(
"--timeout", type=float, default=7200.0, help="HTTP timeout (seconds)."
)
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.",
)
-1
View File
@@ -4,7 +4,6 @@ version = "0.1.0"
description = "Benchmarking tool for exo distributed inference"
requires-python = ">=3.13"
dependencies = [
"httpx>=0.27.0",
"loguru>=0.7.3",
"transformers>=5.0.0",
"huggingface-hub>=0.33.4",
-306
View File
@@ -1,306 +0,0 @@
# Tool definitions — each becomes an OpenAI function tool.
# All scenarios get all tools unless they specify a `tools` list.
[tools.get_current_weather]
description = "Get the current weather in a given location"
required = ["location"]
[tools.get_current_weather.properties.location]
type = "string"
description = "City and state, e.g. San Francisco, CA"
[tools.get_current_weather.properties.unit]
type = "string"
enum = ["celsius", "fahrenheit"]
description = "Temperature unit"
[tools.calculate]
description = "Evaluate a mathematical expression and return the numeric result"
required = ["expression"]
[tools.calculate.properties.expression]
type = "string"
description = "The math expression to evaluate, e.g. '2 + 3 * 4'"
[tools.search_products]
description = "Search for products in a catalog by query, category, and price"
required = ["query"]
[tools.search_products.properties.query]
type = "string"
description = "Search query string"
[tools.search_products.properties.category]
type = "string"
enum = ["electronics", "clothing", "food", "books"]
description = "Product category to filter by"
[tools.search_products.properties.max_price]
type = "number"
description = "Maximum price in USD"
[tools.create_todos]
description = "Create a structured todo list"
required = ["todos"]
[tools.create_todos.properties.todos]
type = "array"
description = "List of todo items"
[tools.create_todos.properties.todos.items]
type = "object"
required = ["content", "status", "priority"]
[tools.create_todos.properties.todos.items.properties.content]
type = "string"
description = "The todo item text"
[tools.create_todos.properties.todos.items.properties.status]
type = "string"
description = "Status: pending, in_progress, or completed"
[tools.create_todos.properties.todos.items.properties.priority]
type = "string"
description = "Priority: low, normal, or high"
# -- Should call a tool --
[[scenarios]]
name = "weather_simple"
description = "Basic weather query -> get_current_weather"
expect_tool_call = true
expected_function = "get_current_weather"
required_arg_keys = ["location"]
[[scenarios.messages]]
role = "user"
content = "What's the weather like in Tokyo right now?"
[[scenarios]]
name = "calculator_simple"
description = "Math question -> calculate"
expect_tool_call = true
expected_function = "calculate"
required_arg_keys = ["expression"]
[[scenarios.messages]]
role = "user"
content = "Use the calculator to compute 3847 * 926 + 17293"
[[scenarios]]
name = "search_with_filters"
description = "Product search with category and price filter"
expect_tool_call = true
expected_function = "search_products"
required_arg_keys = ["query"]
[[scenarios.messages]]
role = "user"
content = "Find me electronics under $50"
# -- Multi-turn: tool call then follow-up --
[[scenarios]]
name = "weather_multi_turn"
description = "Weather query -> tool result -> natural language summary"
expect_tool_call = true
expected_function = "get_current_weather"
required_arg_keys = ["location"]
[scenarios.tool_result]
temperature = "18C"
condition = "partly cloudy"
humidity = "65%"
wind = "12 km/h NW"
[[scenarios.messages]]
role = "user"
content = "What's the weather in Paris?"
[[scenarios]]
name = "calculator_multi_turn"
description = "Math query -> tool result -> model reports the answer"
expect_tool_call = true
expected_function = "calculate"
required_arg_keys = ["expression"]
[scenarios.tool_result]
result = 491682
[[scenarios.messages]]
role = "user"
content = "Use the calculator to compute 1847 * 263 + 5921"
[[scenarios]]
name = "search_multi_turn"
description = "Search query -> tool result -> model summarizes products"
expect_tool_call = true
expected_function = "search_products"
required_arg_keys = ["query"]
[[scenarios.tool_result.results]]
name = "Hands-On Machine Learning"
price = 45.99
rating = 4.8
[[scenarios.tool_result.results]]
name = "Deep Learning with Python"
price = 39.99
rating = 4.6
[[scenarios.messages]]
role = "user"
content = "Search for books about machine learning"
# -- Sequential tool calls --
[[scenarios]]
name = "chained_tool_calls_same"
description = "Thinking + weather(Tokyo) -> result -> model must call weather(London)"
expect_tool_call = true
expected_function = "get_current_weather"
required_arg_keys = ["location"]
[[scenarios.messages]]
role = "user"
content = "Compare the weather in Tokyo and London."
[[scenarios.messages]]
role = "assistant"
content = "I'll check both cities. Let me start with Tokyo."
[[scenarios.messages.tool_calls]]
id = "call_1"
name = "get_current_weather"
arguments = { location = "Tokyo" }
[[scenarios.messages]]
role = "tool"
tool_call_id = "call_1"
content = '{"temperature": "25C", "condition": "sunny"}'
[[scenarios]]
name = "chained_tool_calls_different"
description = "Thinking + weather(Berlin) -> result -> model must call calculator"
expect_tool_call = true
expected_function = "calculate"
required_arg_keys = ["expression"]
[[scenarios.messages]]
role = "user"
content = "What's the weather in Berlin, and also use the calculator to compute 4819 * 37 + 291."
[[scenarios.messages]]
role = "assistant"
content = "I'll handle both. Let me check Berlin's weather first."
[[scenarios.messages.tool_calls]]
id = "call_2"
name = "get_current_weather"
arguments = { location = "Berlin" }
[[scenarios.messages]]
role = "tool"
tool_call_id = "call_2"
content = '{"temperature": "12C", "condition": "rainy"}'
[[scenarios]]
name = "chained_tool_calls_three"
description = "Two prior thinking+tool calls -> results -> model must make a third"
expect_tool_call = true
expected_function = "get_current_weather"
required_arg_keys = ["location"]
[[scenarios.messages]]
role = "user"
content = "Compare weather in Tokyo, Paris, and London."
[[scenarios.messages]]
role = "assistant"
content = "I'll check all three cities. Starting with Tokyo."
[[scenarios.messages.tool_calls]]
id = "call_3"
name = "get_current_weather"
arguments = { location = "Tokyo" }
[[scenarios.messages]]
role = "tool"
tool_call_id = "call_3"
content = '{"temperature": "25C", "condition": "sunny"}'
[[scenarios.messages]]
role = "assistant"
content = "Got Tokyo. Now checking Paris."
[[scenarios.messages.tool_calls]]
id = "call_4"
name = "get_current_weather"
arguments = { location = "Paris" }
[[scenarios.messages]]
role = "tool"
tool_call_id = "call_4"
content = '{"temperature": "18C", "condition": "cloudy"}'
# -- Nested object schema (regression for lossy chat template rendering) --
[[scenarios]]
name = "nested_schema_tool_call"
description = "Tool call with nested object array schema -> create_todos"
expect_tool_call = true
expected_function = "create_todos"
required_arg_keys = ["todos"]
nested_array_key = "todos"
required_item_keys = ["content", "status", "priority"]
tools = ["create_todos"]
[[scenarios.messages]]
role = "user"
content = "Create a todo list with 3 items to learn Python"
# -- Tool name integrity (regression for harmony token leaking into name) --
[tools.glob]
description = "Search for files matching a glob pattern in the codebase"
required = ["pattern"]
[tools.glob.properties.pattern]
type = "string"
description = "The glob pattern to match files against, e.g. '**/*.py'"
[tools.glob.properties.path]
type = "string"
description = "The directory to search in"
[[scenarios]]
name = "tool_name_integrity"
description = "Tool name must not contain harmony tokens like <|channel|>"
expect_tool_call = true
expected_function = "glob"
required_arg_keys = ["pattern"]
tools = ["glob"]
[[scenarios.messages]]
role = "user"
content = "Find all Python files in the src directory"
# -- Should NOT call a tool --
[[scenarios]]
name = "no_tool_joke"
description = "Joke request should NOT trigger any tool"
expect_tool_call = false
[[scenarios.messages]]
role = "user"
content = "Tell me a funny joke about cats."
[[scenarios]]
name = "no_tool_factual"
description = "Factual question answerable from training data"
expect_tool_call = false
[[scenarios.messages]]
role = "user"
content = "What is the capital of Japan?"
-189
View File
@@ -1,189 +0,0 @@
# Single-node M3 Ultra benchmarks
#
# Shared constraints applied to ALL benchmarks in this file.
constraints = [
"All(MacOsBuild(=25D125))",
"Hosts(=1)",
"All(Chip(m3_ultra))",
"All(GpuCores(=80))",
]
[topology]
type = "none"
# Default args merged into each benchmark's args (benchmark-level args win).
[defaults]
pp = [512, 2048, 8192, 16384]
tg = 128
[[benchmark]]
model = "mlx-community/Meta-Llama-3.1-70B-Instruct-4bit"
extra_constraints = ["All(Memory(>=96GiB))"]
[[benchmark]]
model = "mlx-community/gpt-oss-120b-MXFP4-Q8"
extra_constraints = ["All(Memory(>=96GiB))"]
[[benchmark]]
model = "mlx-community/GLM-4.7-Flash-8bit"
extra_constraints = ["All(Memory(>=96GiB))"]
[[benchmark]]
model = "mlx-community/Qwen3-Coder-Next-6bit"
extra_constraints = ["All(Memory(>=96GiB))"]
[[benchmark]]
model = "mlx-community/Qwen3-30B-A3B-8bit"
extra_constraints = ["All(Memory(>=96GiB))"]
[[benchmark]]
model = "mlx-community/Qwen3-0.6B-4bit"
extra_constraints = ["All(Memory(>=96GiB))"]
[[benchmark]]
model = "mlx-community/Qwen3-0.6B-8bit"
extra_constraints = ["All(Memory(>=96GiB))"]
[[benchmark]]
model = "mlx-community/Llama-3.2-1B-Instruct-4bit"
extra_constraints = ["All(Memory(>=96GiB))"]
[[benchmark]]
model = "mlx-community/Llama-3.2-3B-Instruct-4bit"
extra_constraints = ["All(Memory(>=96GiB))"]
[[benchmark]]
model = "mlx-community/Llama-3.2-3B-Instruct-8bit"
extra_constraints = ["All(Memory(>=96GiB))"]
[[benchmark]]
model = "mlx-community/Meta-Llama-3.1-8B-Instruct-4bit"
extra_constraints = ["All(Memory(>=96GiB))"]
[[benchmark]]
model = "mlx-community/Meta-Llama-3.1-8B-Instruct-8bit"
extra_constraints = ["All(Memory(>=96GiB))"]
[[benchmark]]
model = "mlx-community/Meta-Llama-3.1-8B-Instruct-bf16"
extra_constraints = ["All(Memory(>=96GiB))"]
[[benchmark]]
model = "mlx-community/gpt-oss-20b-MXFP4-Q8"
extra_constraints = ["All(Memory(>=96GiB))"]
[[benchmark]]
model = "mlx-community/Qwen3-30B-A3B-4bit"
extra_constraints = ["All(Memory(>=96GiB))"]
[[benchmark]]
model = "mlx-community/GLM-4.7-Flash-4bit"
extra_constraints = ["All(Memory(>=96GiB))"]
[[benchmark]]
model = "mlx-community/GLM-4.7-Flash-5bit"
extra_constraints = ["All(Memory(>=96GiB))"]
[[benchmark]]
model = "mlx-community/GLM-4.7-Flash-6bit"
extra_constraints = ["All(Memory(>=96GiB))"]
[[benchmark]]
model = "mlx-community/Llama-3.3-70B-Instruct-4bit"
extra_constraints = ["All(Memory(>=96GiB))"]
[[benchmark]]
model = "mlx-community/Qwen3-Coder-Next-4bit"
extra_constraints = ["All(Memory(>=96GiB))"]
[[benchmark]]
model = "mlx-community/Qwen3-Coder-Next-5bit"
extra_constraints = ["All(Memory(>=96GiB))"]
[[benchmark]]
model = "mlx-community/Qwen3-Coder-Next-8bit"
extra_constraints = ["All(Memory(>=96GiB))"]
[[benchmark]]
model = "mlx-community/Qwen3-Next-80B-A3B-Instruct-4bit"
extra_constraints = ["All(Memory(>=96GiB))"]
[[benchmark]]
model = "mlx-community/Qwen3-Next-80B-A3B-Instruct-8bit"
extra_constraints = ["All(Memory(>=96GiB))"]
[[benchmark]]
model = "mlx-community/Qwen3-Next-80B-A3B-Thinking-4bit"
extra_constraints = ["All(Memory(>=96GiB))"]
[[benchmark]]
model = "mlx-community/Qwen3-Next-80B-A3B-Thinking-8bit"
extra_constraints = ["All(Memory(>=96GiB))"]
[[benchmark]]
model = "mlx-community/Llama-3.3-70B-Instruct-8bit"
extra_constraints = ["All(Memory(>=256GiB))"]
[[benchmark]]
model = "mlx-community/llama-3.3-70b-instruct-fp16"
extra_constraints = ["All(Memory(>=256GiB))"]
[[benchmark]]
model = "mlx-community/GLM-4.5-Air-8bit"
extra_constraints = ["All(Memory(>=256GiB))"]
[[benchmark]]
model = "mlx-community/GLM-4.5-Air-bf16"
extra_constraints = ["All(Memory(>=256GiB))"]
[[benchmark]]
model = "mlx-community/GLM-4.7-4bit"
extra_constraints = ["All(Memory(>=256GiB))"]
[[benchmark]]
model = "mlx-community/MiniMax-M2.1-3bit"
extra_constraints = ["All(Memory(>=256GiB))"]
[[benchmark]]
model = "mlx-community/MiniMax-M2.1-8bit"
extra_constraints = ["All(Memory(>=256GiB))"]
[[benchmark]]
model = "mlx-community/Qwen3-235B-A22B-Instruct-2507-4bit"
extra_constraints = ["All(Memory(>=256GiB))"]
[[benchmark]]
model = "mlx-community/Qwen3-Coder-Next-bf16"
extra_constraints = ["All(Memory(>=256GiB))"]
[[benchmark]]
model = "mlx-community/Step-3.5-Flash-4bit"
extra_constraints = ["All(Memory(>=256GiB))"]
[[benchmark]]
model = "mlx-community/Step-3.5-Flash-6bit"
extra_constraints = ["All(Memory(>=256GiB))"]
[[benchmark]]
model = "mlx-community/Step-3.5-Flash-8Bit"
extra_constraints = ["All(Memory(>=256GiB))"]
[[benchmark]]
model = "mlx-community/DeepSeek-V3.1-4bit"
extra_constraints = ["All(Memory(>=512GiB))"]
[[benchmark]]
model = "mlx-community/GLM-4.7-6bit"
extra_constraints = ["All(Memory(>=512GiB))"]
[[benchmark]]
model = "mlx-community/GLM-4.7-8bit-gs32"
extra_constraints = ["All(Memory(>=512GiB))"]
[[benchmark]]
model = "mlx-community/Qwen3-235B-A22B-Instruct-2507-8bit"
extra_constraints = ["All(Memory(>=512GiB))"]
[[benchmark]]
model = "mlx-community/Qwen3-Coder-480B-A35B-Instruct-4bit"
extra_constraints = ["All(Memory(>=512GiB))"]
+81 -136
View File
@@ -12,9 +12,6 @@
ttftMs,
tps,
totalTokens,
thinkingEnabled as thinkingEnabledStore,
setConversationThinking,
stopGeneration,
} from "$lib/stores/app.svelte";
import ChatAttachments from "./ChatAttachments.svelte";
import ImageParamsPanel from "./ImageParamsPanel.svelte";
@@ -28,7 +25,6 @@
autofocus?: boolean;
showModelSelector?: boolean;
modelTasks?: Record<string, string[]>;
modelCapabilities?: Record<string, string[]>;
}
let {
@@ -38,7 +34,6 @@
autofocus = true,
showModelSelector = false,
modelTasks = {},
modelCapabilities = {},
}: Props = $props();
let message = $state("");
@@ -46,7 +41,6 @@
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());
@@ -101,12 +95,6 @@
);
});
const modelSupportsThinking = $derived(() => {
if (!currentModel) return false;
const caps = modelCapabilities[currentModel] || [];
return caps.includes("thinking_toggle") && caps.includes("text");
});
const isEditOnlyWithoutImage = $derived(
currentModel !== null &&
modelSupportsOnlyImageEditing(currentModel) &&
@@ -266,7 +254,6 @@
function handleSubmit() {
if ((!message.trim() && uploadedFiles.length === 0) || loading) return;
if (isEditOnlyWithoutImage) return;
const content = message.trim();
const files = [...uploadedFiles];
@@ -291,19 +278,11 @@
if (imageFile.preview) {
editImage(content, imageFile.preview);
}
} else if (
currentModel &&
modelSupportsTextToImage(currentModel) &&
content
) {
} else if (isImageModel() && content) {
// Use image generation for text-to-image models
generateImage(content);
} else {
sendMessage(
content,
files,
modelSupportsThinking() ? thinkingEnabled : null,
);
sendMessage(content, files);
}
// Refocus the textarea after sending
@@ -541,35 +520,6 @@
</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">
@@ -649,97 +599,92 @@
: 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 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 disabled:opacity-50 text-sm leading-7 font-mono"
style="min-height: 28px; max-height: 150px;"
></textarea>
{#if loading}
<button
type="button"
onclick={() => stopGeneration()}
class="px-2.5 sm:px-4 py-1.5 sm:py-2 rounded text-xs sm:text-xs tracking-[0.1em] sm:tracking-[0.15em] font-medium transition-all duration-200 whitespace-nowrap bg-exo-medium-gray/70 text-exo-light-gray hover:bg-exo-medium-gray hover:text-white"
aria-label="Stop generation"
>
<button
type="submit"
disabled={!canSend || loading || isEditOnlyWithoutImage}
class="px-2.5 sm:px-4 py-1.5 sm:py-2 rounded text-xs sm:text-xs tracking-[0.1em] sm:tracking-[0.15em] uppercase font-medium transition-all duration-200 whitespace-nowrap
{!canSend || loading || isEditOnlyWithoutImage
? 'bg-exo-medium-gray/50 text-exo-light-gray cursor-not-allowed'
: 'bg-exo-yellow text-exo-black hover:bg-exo-yellow-darker hover:shadow-[0_0_20px_rgba(255,215,0,0.3)]'}"
aria-label={shouldShowEditMode
? "Edit image"
: isImageModel()
? "Generate image"
: "Send message"}
>
{#if loading}
<span class="inline-flex items-center gap-1 sm:gap-2">
<svg
class="w-3 h-3 sm:w-3.5 sm:h-3.5"
fill="currentColor"
viewBox="0 0 24 24"
<span
class="w-2.5 h-2.5 sm:w-3 sm:h-3 border-2 border-current border-t-transparent rounded-full animate-spin"
></span>
<span class="hidden sm:inline"
>{shouldShowEditMode
? "EDITING"
: isImageModel()
? "GENERATING"
: "PROCESSING"}</span
>
<rect x="6" y="6" width="12" height="12" rx="1" />
</svg>
<span class="hidden sm:inline">Cancel</span>
<span class="sm:hidden">...</span>
</span>
</button>
{:else}
<button
type="submit"
disabled={!canSend || isEditOnlyWithoutImage}
class="px-2.5 sm:px-4 py-1.5 sm:py-2 rounded text-xs sm:text-xs tracking-[0.1em] sm:tracking-[0.15em] uppercase font-medium transition-all duration-200 whitespace-nowrap
{!canSend || isEditOnlyWithoutImage
? 'bg-exo-medium-gray/50 text-exo-light-gray cursor-not-allowed'
: 'bg-exo-yellow text-exo-black hover:bg-exo-yellow-darker hover:shadow-[0_0_20px_rgba(255,215,0,0.3)]'}"
aria-label={shouldShowEditMode
? "Edit image"
: isImageModel()
? "Generate image"
: "Send message"}
>
{#if shouldShowEditMode}
<span class="inline-flex items-center gap-1.5">
<svg
class="w-3.5 h-3.5"
fill="none"
viewBox="0 0 24 24"
stroke="currentColor"
stroke-width="2"
>
<path
stroke-linecap="round"
stroke-linejoin="round"
d="M11 5H6a2 2 0 00-2 2v11a2 2 0 002 2h11a2 2 0 002-2v-5m-1.414-9.414a2 2 0 112.828 2.828L11.828 15H9v-2.828l8.586-8.586z"
/>
</svg>
<span>EDIT</span>
</span>
{:else if isEditOnlyWithoutImage}
<span class="inline-flex items-center gap-1.5">
<svg
class="w-3.5 h-3.5"
fill="none"
viewBox="0 0 24 24"
stroke="currentColor"
stroke-width="2"
>
<path
stroke-linecap="round"
stroke-linejoin="round"
d="M11 5H6a2 2 0 00-2 2v11a2 2 0 002 2h11a2 2 0 002-2v-5m-1.414-9.414a2 2 0 112.828 2.828L11.828 15H9v-2.828l8.586-8.586z"
/>
</svg>
<span>EDIT</span>
</span>
{:else if isImageModel()}
<span class="inline-flex items-center gap-1.5">
<svg
class="w-3.5 h-3.5"
fill="none"
viewBox="0 0 24 24"
stroke="currentColor"
stroke-width="2"
>
<rect x="3" y="3" width="18" height="18" rx="2" ry="2" />
<circle cx="8.5" cy="8.5" r="1.5" />
<polyline points="21 15 16 10 5 21" />
</svg>
<span>GENERATE</span>
</span>
{:else}
SEND
{/if}
</button>
{/if}
{:else if shouldShowEditMode}
<span class="inline-flex items-center gap-1.5">
<svg
class="w-3.5 h-3.5"
fill="none"
viewBox="0 0 24 24"
stroke="currentColor"
stroke-width="2"
>
<path
stroke-linecap="round"
stroke-linejoin="round"
d="M11 5H6a2 2 0 00-2 2v11a2 2 0 002 2h11a2 2 0 002-2v-5m-1.414-9.414a2 2 0 112.828 2.828L11.828 15H9v-2.828l8.586-8.586z"
/>
</svg>
<span>EDIT</span>
</span>
{:else if isEditOnlyWithoutImage}
<span class="inline-flex items-center gap-1.5">
<svg
class="w-3.5 h-3.5"
fill="none"
viewBox="0 0 24 24"
stroke="currentColor"
stroke-width="2"
>
<path
stroke-linecap="round"
stroke-linejoin="round"
d="M11 5H6a2 2 0 00-2 2v11a2 2 0 002 2h11a2 2 0 002-2v-5m-1.414-9.414a2 2 0 112.828 2.828L11.828 15H9v-2.828l8.586-8.586z"
/>
</svg>
<span>EDIT</span>
</span>
{:else if isImageModel()}
<span class="inline-flex items-center gap-1.5">
<svg
class="w-3.5 h-3.5"
fill="none"
viewBox="0 0 24 24"
stroke="currentColor"
stroke-width="2"
>
<rect x="3" y="3" width="18" height="18" rx="2" ry="2" />
<circle cx="8.5" cy="8.5" r="1.5" />
<polyline points="21 15 16 10 5 21" />
</svg>
<span>GENERATE</span>
</span>
{:else}
SEND
{/if}
</button>
</div>
<!-- Bottom accent line -->
@@ -3,17 +3,16 @@
messages,
currentResponse,
isLoading,
prefillProgress,
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 PrefillProgressBar from "./PrefillProgressBar.svelte";
import ImageLightbox from "./ImageLightbox.svelte";
interface Props {
@@ -26,7 +25,6 @@
const messageList = $derived(messages());
const response = $derived(currentResponse());
const loading = $derived(isLoading());
const prefill = $derived(prefillProgress());
// Scroll management - user controls scroll, show button when not at bottom
const SCROLL_THRESHOLD = 100;
@@ -227,7 +225,6 @@
}
function handleDeleteClick(messageId: string) {
if (loading) return;
deleteConfirmId = messageId;
}
@@ -258,7 +255,7 @@
</script>
<div class="flex flex-col gap-4 sm:gap-6 {className}">
{#each messageList as message, i (message.id)}
{#each messageList as message (message.id)}
<div
class="group flex {message.role === 'user'
? 'justify-end'
@@ -320,11 +317,9 @@
<!-- 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">
{#if i === messageList.length - 1}
Delete this message?
{:else}
Delete this message and all messages after it?
{/if}
Delete this message{message.role === "user"
? " and all responses after it"
: ""}?
</p>
<div class="flex gap-2 justify-end">
<button
@@ -430,9 +425,6 @@
{:else}
<!-- Assistant message styling -->
<div class="p-3 sm:p-4">
{#if loading && isLastAssistantMessage(message.id) && prefill && !message.content}
<PrefillProgressBar progress={prefill} class="mb-3" />
{/if}
{#if message.thinking && message.thinking.trim().length > 0}
<div
class="mb-3 rounded border border-exo-yellow/20 bg-exo-black/40"
@@ -759,13 +751,8 @@
<!-- Delete button -->
<button
onclick={() => handleDeleteClick(message.id)}
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"}
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"
>
<svg
class="w-3.5 h-3.5"
@@ -13,12 +13,6 @@
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
@@ -5,22 +5,15 @@
families: string[];
selectedFamily: string | null;
hasFavorites: boolean;
hasRecents: boolean;
onSelect: (family: string | null) => void;
};
let {
families,
selectedFamily,
hasFavorites,
hasRecents,
onSelect,
}: FamilySidebarProps = $props();
let { families, selectedFamily, hasFavorites, onSelect }: FamilySidebarProps =
$props();
// Family display names
const familyNames: Record<string, string> = {
favorites: "Favorites",
recents: "Recent",
huggingface: "Hub",
llama: "Meta",
qwen: "Qwen",
@@ -96,31 +89,6 @@
</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"
@@ -26,8 +26,7 @@
downloadedOnNodes = [],
}: HuggingFaceResultItemProps = $props();
function formatNumber(num: number | undefined): string {
if (num == null) return "0";
function formatNumber(num: number): string {
if (num >= 1000000) {
return `${(num / 1000000).toFixed(1)}M`;
} else if (num >= 1000) {
@@ -59,14 +59,13 @@
}
const sizeOptions: ImageGenerationParams["size"][] = [
"auto",
"512x512",
"768x768",
"1024x1024",
"1024x768",
"768x1024",
"1024x1536",
"1536x1024",
"1024x1365",
"1365x1024",
];
const qualityOptions: ImageGenerationParams["quality"][] = [
@@ -177,90 +176,92 @@
<div class="border-b border-exo-medium-gray/30 px-3 py-2">
<!-- Basic params row -->
<div class="flex items-center gap-3 flex-wrap">
<!-- Size -->
<div class="flex items-center gap-1.5">
<span class="text-xs text-exo-light-gray uppercase tracking-wider"
>SIZE:</span
>
<div class="relative">
<button
bind:this={sizeButtonRef}
type="button"
onclick={() => (isSizeDropdownOpen = !isSizeDropdownOpen)}
class="bg-exo-medium-gray/50 border border-exo-yellow/30 rounded pl-2 pr-6 py-1 text-xs font-mono text-exo-yellow cursor-pointer transition-all duration-200 hover:border-exo-yellow/50 focus:outline-none focus:border-exo-yellow/70 {isSizeDropdownOpen
? 'border-exo-yellow/70'
: ''}"
<!-- Size (hidden in edit mode - output size comes from input image) -->
{#if !isEditMode}
<div class="flex items-center gap-1.5">
<span class="text-xs text-exo-light-gray uppercase tracking-wider"
>SIZE:</span
>
{params.size.toUpperCase()}
</button>
<div
class="absolute right-1.5 top-1/2 -translate-y-1/2 pointer-events-none transition-transform duration-200 {isSizeDropdownOpen
? 'rotate-180'
: ''}"
>
<svg
class="w-3 h-3 text-exo-yellow/60"
fill="none"
viewBox="0 0 24 24"
stroke="currentColor"
<div class="relative">
<button
bind:this={sizeButtonRef}
type="button"
onclick={() => (isSizeDropdownOpen = !isSizeDropdownOpen)}
class="bg-exo-medium-gray/50 border border-exo-yellow/30 rounded pl-2 pr-6 py-1 text-xs font-mono text-exo-yellow cursor-pointer transition-all duration-200 hover:border-exo-yellow/50 focus:outline-none focus:border-exo-yellow/70 {isSizeDropdownOpen
? 'border-exo-yellow/70'
: ''}"
>
<path
stroke-linecap="round"
stroke-linejoin="round"
stroke-width="2"
d="M19 9l-7 7-7-7"
/>
</svg>
</div>
</div>
{#if isSizeDropdownOpen}
<!-- Backdrop to close dropdown -->
<button
type="button"
class="fixed inset-0 z-[9998] cursor-default"
onclick={() => (isSizeDropdownOpen = false)}
aria-label="Close dropdown"
></button>
<!-- Dropdown Panel - fixed positioning to escape overflow:hidden -->
<div
class="fixed bg-exo-dark-gray border border-exo-yellow/30 rounded shadow-lg shadow-black/50 z-[9999] max-h-48 overflow-y-auto overflow-x-hidden min-w-max"
style="bottom: calc(100vh - {sizeDropdownPosition()
.top}px + 4px); left: {sizeDropdownPosition().left}px;"
>
<div class="py-1">
{#each sizeOptions as size}
<button
type="button"
onclick={() => selectSize(size)}
class="w-full px-3 py-1.5 text-left text-xs font-mono tracking-wide transition-colors duration-100 flex items-center gap-2 {params.size ===
size
? 'bg-transparent text-exo-yellow'
: 'text-exo-light-gray hover:text-exo-yellow'}"
>
{#if params.size === size}
<svg
class="w-3 h-3 flex-shrink-0"
fill="currentColor"
viewBox="0 0 20 20"
>
<path
fill-rule="evenodd"
d="M16.707 5.293a1 1 0 010 1.414l-8 8a1 1 0 01-1.414 0l-4-4a1 1 0 011.414-1.414L8 12.586l7.293-7.293a1 1 0 011.414 0z"
clip-rule="evenodd"
/>
</svg>
{:else}
<span class="w-3"></span>
{/if}
<span>{size.toUpperCase()}</span>
</button>
{/each}
{params.size}
</button>
<div
class="absolute right-1.5 top-1/2 -translate-y-1/2 pointer-events-none transition-transform duration-200 {isSizeDropdownOpen
? 'rotate-180'
: ''}"
>
<svg
class="w-3 h-3 text-exo-yellow/60"
fill="none"
viewBox="0 0 24 24"
stroke="currentColor"
>
<path
stroke-linecap="round"
stroke-linejoin="round"
stroke-width="2"
d="M19 9l-7 7-7-7"
/>
</svg>
</div>
</div>
{/if}
</div>
{#if isSizeDropdownOpen}
<!-- Backdrop to close dropdown -->
<button
type="button"
class="fixed inset-0 z-[9998] cursor-default"
onclick={() => (isSizeDropdownOpen = false)}
aria-label="Close dropdown"
></button>
<!-- Dropdown Panel - fixed positioning to escape overflow:hidden -->
<div
class="fixed bg-exo-dark-gray border border-exo-yellow/30 rounded shadow-lg shadow-black/50 z-[9999] max-h-48 overflow-y-auto min-w-max"
style="bottom: calc(100vh - {sizeDropdownPosition()
.top}px + 4px); left: {sizeDropdownPosition().left}px;"
>
<div class="py-1">
{#each sizeOptions as size}
<button
type="button"
onclick={() => selectSize(size)}
class="w-full px-3 py-1.5 text-left text-xs font-mono tracking-wide transition-colors duration-100 flex items-center gap-2 {params.size ===
size
? 'bg-transparent text-exo-yellow'
: 'text-exo-light-gray hover:text-exo-yellow'}"
>
{#if params.size === size}
<svg
class="w-3 h-3 flex-shrink-0"
fill="currentColor"
viewBox="0 0 20 20"
>
<path
fill-rule="evenodd"
d="M16.707 5.293a1 1 0 010 1.414l-8 8a1 1 0 01-1.414 0l-4-4a1 1 0 011.414-1.414L8 12.586l7.293-7.293a1 1 0 011.414 0z"
clip-rule="evenodd"
/>
</svg>
{:else}
<span class="w-3"></span>
{/if}
<span>{size}</span>
</button>
{/each}
</div>
</div>
{/if}
</div>
{/if}
<!-- Quality -->
<div class="flex items-center gap-1.5">
@@ -310,7 +311,7 @@
<!-- Dropdown Panel - fixed positioning to escape overflow:hidden -->
<div
class="fixed bg-exo-dark-gray border border-exo-yellow/30 rounded shadow-lg shadow-black/50 z-[9999] max-h-48 overflow-y-auto overflow-x-hidden min-w-max"
class="fixed bg-exo-dark-gray border border-exo-yellow/30 rounded shadow-lg shadow-black/50 z-[9999] max-h-48 overflow-y-auto min-w-max"
style="bottom: calc(100vh - {qualityDropdownPosition()
.top}px + 4px); left: {qualityDropdownPosition().left}px;"
>
@@ -1,232 +0,0 @@
<script lang="ts">
import type {
MetaInstance,
MetaInstanceStatus,
NodeInfo,
} from "$lib/stores/app.svelte";
import {
getMetaInstanceStatus,
getMetaInstanceBackingNodes,
topologyData,
} from "$lib/stores/app.svelte";
interface Props {
metaInstance: MetaInstance;
onDelete?: (metaInstanceId: string) => void;
}
let { metaInstance, onDelete }: Props = $props();
const status: MetaInstanceStatus = $derived(
getMetaInstanceStatus(metaInstance),
);
const backingNodeIds: string[] = $derived(
getMetaInstanceBackingNodes(metaInstance),
);
const statusConfig = $derived.by(() => {
switch (status) {
case "active":
return {
label: "ACTIVE",
dotClass: "bg-green-400",
borderClass:
"border-green-500/30 border-l-green-400",
cornerClass: "border-green-500/50",
glowClass: "shadow-[0_0_6px_rgba(74,222,128,0.4)]",
animate: false,
};
case "provisioning":
return {
label: "PROVISIONING",
dotClass: "bg-yellow-400",
borderClass:
"border-exo-yellow/30 border-l-yellow-400",
cornerClass: "border-yellow-500/50",
glowClass: "shadow-[0_0_6px_rgba(250,204,21,0.4)]",
animate: true,
};
case "error":
return {
label: "ERROR",
dotClass: "bg-red-400",
borderClass: "border-red-500/30 border-l-red-400",
cornerClass: "border-red-500/50",
glowClass: "shadow-[0_0_6px_rgba(248,113,113,0.4)]",
animate: false,
};
}
});
function getNodeName(nodeId: string): string {
const topo = topologyData();
if (!topo?.nodes) return nodeId.slice(0, 8);
const node = topo.nodes[nodeId];
return node?.friendly_name || node?.system_info?.model_id || nodeId.slice(0, 8);
}
function formatModelId(modelId: string): string {
// Show just the model name part after the org prefix
const parts = modelId.split("/");
return parts.length > 1 ? parts[parts.length - 1] : modelId;
}
function handleDelete() {
if (
onDelete &&
confirm(
`Delete meta-instance for ${formatModelId(metaInstance.modelId)}?`,
)
) {
onDelete(metaInstance.metaInstanceId);
}
}
</script>
<div class="relative group">
<!-- Corner accents -->
<div
class="absolute -top-px -left-px w-2 h-2 border-l border-t {statusConfig.cornerClass}"
></div>
<div
class="absolute -top-px -right-px w-2 h-2 border-r border-t {statusConfig.cornerClass}"
></div>
<div
class="absolute -bottom-px -left-px w-2 h-2 border-l border-b {statusConfig.cornerClass}"
></div>
<div
class="absolute -bottom-px -right-px w-2 h-2 border-r border-b {statusConfig.cornerClass}"
></div>
<div
class="bg-exo-dark-gray/60 border border-l-2 {statusConfig.borderClass} p-3"
>
<!-- Header: Status + Delete -->
<div class="flex justify-between items-start mb-2 pl-2">
<div class="flex items-center gap-2">
<div
class="w-1.5 h-1.5 {statusConfig.dotClass} rounded-full {statusConfig.glowClass} {statusConfig.animate
? 'animate-pulse'
: ''}"
></div>
<span
class="text-xs font-mono tracking-[0.15em] uppercase {status === 'active'
? 'text-green-400'
: status === 'error'
? 'text-red-400'
: 'text-yellow-400'}"
>
{statusConfig.label}
</span>
</div>
<button
onclick={handleDelete}
class="text-xs px-2 py-1 font-mono tracking-wider uppercase border border-red-500/30 text-red-400 hover:bg-red-500/20 hover:text-red-400 hover:border-red-500/50 transition-all duration-200 cursor-pointer"
>
DELETE
</button>
</div>
<!-- Model Info -->
<div class="pl-2 space-y-1">
<div class="text-exo-yellow text-xs font-mono tracking-wide truncate">
{metaInstance.modelId}
</div>
<!-- Sharding + Runtime badges -->
<div class="flex items-center gap-2">
<span
class="inline-flex items-center px-1.5 py-0.5 text-[10px] font-mono tracking-wider uppercase border border-white/10 text-white/50"
>
{metaInstance.sharding}
</span>
<span
class="inline-flex items-center px-1.5 py-0.5 text-[10px] font-mono tracking-wider uppercase border border-white/10 text-white/50"
>
{metaInstance.instanceMeta}
</span>
{#if metaInstance.minNodes > 1}
<span
class="inline-flex items-center px-1.5 py-0.5 text-[10px] font-mono tracking-wider uppercase border border-white/10 text-white/50"
>
{metaInstance.minNodes}+ nodes
</span>
{/if}
</div>
<!-- Node Assignments (when active) -->
{#if backingNodeIds.length > 0}
<div class="flex items-center gap-1.5 mt-1">
<svg
class="w-3 h-3 text-green-400/70 flex-shrink-0"
viewBox="0 0 24 24"
fill="none"
stroke="currentColor"
stroke-width="2"
>
<path
d="M22 12h-4l-3 9L9 3l-3 9H2"
stroke-linecap="round"
stroke-linejoin="round"
/>
</svg>
<span class="text-white/60 text-xs font-mono truncate">
{backingNodeIds.map((id) => getNodeName(id)).join(", ")}
</span>
</div>
{/if}
<!-- Pinned nodes constraint -->
{#if metaInstance.nodeIds && metaInstance.nodeIds.length > 0}
<div class="flex items-center gap-1.5">
<svg
class="w-3 h-3 text-white/40 flex-shrink-0"
viewBox="0 0 24 24"
fill="none"
stroke="currentColor"
stroke-width="2"
>
<rect x="3" y="11" width="18" height="11" rx="2" ry="2" />
<path d="M7 11V7a5 5 0 0 1 10 0v4" />
</svg>
<span class="text-white/40 text-[11px] font-mono">
Pinned: {metaInstance.nodeIds
.map((id) => getNodeName(id))
.join(", ")}
</span>
</div>
{/if}
<!-- Error details -->
{#if metaInstance.placementError}
<div
class="mt-1.5 p-2 bg-red-500/5 border border-red-500/15 rounded-sm"
>
<div class="text-red-400 text-[11px] font-mono leading-relaxed">
{metaInstance.placementError}
</div>
</div>
{/if}
<!-- Retry counter -->
{#if metaInstance.consecutiveFailures > 0}
<div class="flex items-center gap-1.5 mt-1">
<svg
class="w-3 h-3 text-yellow-500/60 flex-shrink-0"
viewBox="0 0 24 24"
fill="none"
stroke="currentColor"
stroke-width="2"
>
<polyline points="23 4 23 10 17 10" />
<path d="M20.49 15a9 9 0 1 1-2.12-9.36L23 10" />
</svg>
<span class="text-yellow-500/60 text-[11px] font-mono">
{metaInstance.consecutiveFailures} consecutive
failure{metaInstance.consecutiveFailures !== 1 ? "s" : ""}
</span>
</div>
{/if}
</div>
</div>
</div>
+3 -10
View File
@@ -422,16 +422,9 @@
const bToACandidates: Array<{ ip: string; iface: string | null }> = [];
for (const edge of topology.edges) {
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);
}
const ip = edge.sendBackIp || "?";
const iface =
edge.sendBackInterface || getInterfaceForIp(edge.source, ip);
if (edge.source === nodeId1 && edge.target === nodeId2) {
aToBCandidates.push({ ip, iface });
@@ -26,7 +26,6 @@
nodeNames: string[];
nodeIds: string[];
};
type ModelFitStatus = "fits_now" | "fits_cluster_capacity" | "too_large";
type ModelPickerGroupProps = {
group: ModelGroup;
@@ -34,13 +33,11 @@
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 {
@@ -49,13 +46,11 @@
isFavorite,
selectedModelId,
canModelFit,
getModelFitStatus,
onToggleExpand,
onSelectModel,
onToggleFavorite,
onShowInfo,
downloadStatusMap,
launchedAt,
}: ModelPickerGroupProps = $props();
// Group-level download status: show if any variant is downloaded
@@ -77,45 +72,10 @@
return `${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 = $derived(
@@ -284,14 +244,7 @@
<!-- Size indicator (smallest variant) -->
{#if !group.hasMultipleVariants && group.smallestVariant?.storage_size_megabytes}
{@const singleVariantFitStatus = getModelFitStatus(
group.smallestVariant.id,
)}
<span
class="text-xs font-mono flex-shrink-0 {getSizeClassForFitStatus(
singleVariantFitStatus,
)}"
>
<span class="text-xs font-mono text-white/30 flex-shrink-0">
{formatSize(group.smallestVariant.storage_size_megabytes)}
</span>
{/if}
@@ -302,24 +255,13 @@
.map((v) => v.storage_size_megabytes || 0)
.filter((s) => s > 0)
.sort((a, b) => a - b)}
<span
class="text-xs font-mono flex-shrink-0 {getSizeClassForFitStatus(
groupFitStatus,
)}"
>
<span class="text-xs font-mono text-white/30 flex-shrink-0">
{group.variants.length} variants{#if sizes.length >= 2}{" "}({formatSize(
sizes[0],
)}-{formatSize(sizes[sizes.length - 1])}){/if}
</span>
{/if}
<!-- Time ago (for recent models) -->
{#if launchedAt}
<span class="text-xs font-mono text-white/20 flex-shrink-0">
{timeAgo(launchedAt)}
</span>
{/if}
<!-- Download availability indicator -->
{#if groupDownloadStatus && groupDownloadStatus.nodeIds.length > 0}
<span
@@ -418,7 +360,6 @@
{#if isExpanded && group.hasMultipleVariants}
<div class="bg-black/20 border-t border-white/5">
{#each group.variants as variant}
{@const fitStatus = getModelFitStatus(variant.id)}
{@const modelCanFit = canModelFit(variant.id)}
{@const isSelected = selectedModelId === variant.id}
<button
@@ -443,11 +384,7 @@
</span>
<!-- Size -->
<span
class="text-xs font-mono flex-1 {getSizeClassForFitStatus(
fitStatus,
)}"
>
<span class="text-xs font-mono text-white/40 flex-1">
{formatSize(variant.storage_size_megabytes)}
</span>
@@ -6,7 +6,6 @@
import ModelFilterPopover from "./ModelFilterPopover.svelte";
import HuggingFaceResultItem from "./HuggingFaceResultItem.svelte";
import { getNodesWithModelDownloaded } from "$lib/utils/downloads";
import { getRecentEntries } from "$lib/stores/recents.svelte";
interface ModelInfo {
id: string;
@@ -47,18 +46,13 @@
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;
@@ -82,11 +76,8 @@
models,
selectedModelId,
favorites,
recentModelIds = [],
hasRecents: hasRecentsTab = false,
existingModelIds,
canModelFit,
getModelFitStatus,
onSelect,
onClose,
onToggleFavorite,
@@ -392,11 +383,7 @@
// Filter by family
if (selectedFamily === "favorites") {
result = result.filter((g) => favorites.has(g.id));
} else if (
selectedFamily &&
selectedFamily !== "huggingface" &&
selectedFamily !== "recents"
) {
} else if (selectedFamily && selectedFamily !== "huggingface") {
result = result.filter((g) => g.family === selectedFamily);
}
@@ -440,23 +427,13 @@
);
}
// Sort: fits-now first, then fits-cluster-capacity, then too-large
// Sort: models that fit first, then by size (largest first)
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 aFits = a.variants.some((v) => canModelFit(v.id));
const bFits = b.variants.some((v) => canModelFit(v.id));
const aRank = getGroupFitRank(a);
const bRank = getGroupFitRank(b);
if (aRank !== bRank) return aRank - bRank;
if (aFits && !bFits) return -1;
if (!aFits && bFits) return 1;
return (
(b.smallestVariant.storage_size_megabytes || 0) -
@@ -470,48 +447,6 @@
// 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)) {
@@ -669,7 +604,6 @@
families={uniqueFamilies}
{selectedFamily}
{hasFavorites}
hasRecents={hasRecentsTab}
onSelect={(family) => (selectedFamily = family)}
/>
@@ -777,45 +711,6 @@
</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"
@@ -847,7 +742,6 @@
isFavorite={favorites.has(group.id)}
{selectedModelId}
{canModelFit}
{getModelFitStatus}
onToggleExpand={() => toggleGroupExpanded(group.id)}
onSelectModel={handleSelect}
{onToggleFavorite}
@@ -1,52 +0,0 @@
<script lang="ts">
import type { PrefillProgress } from "$lib/stores/app.svelte";
interface Props {
progress: PrefillProgress;
class?: string;
}
let { progress, class: className = "" }: Props = $props();
const percentage = $derived(
progress.total > 0
? Math.round((progress.processed / progress.total) * 100)
: 0,
);
function formatTokenCount(count: number | undefined): string {
if (count == null) return "0";
if (count >= 1000) {
return `${(count / 1000).toFixed(1)}k`;
}
return count.toString();
}
</script>
<div class="prefill-progress {className}">
<div
class="flex items-center justify-between text-xs text-exo-light-gray mb-1"
>
<span>Processing prompt</span>
<span class="font-mono">
{formatTokenCount(progress.processed)} / {formatTokenCount(
progress.total,
)} tokens
</span>
</div>
<div class="h-1.5 bg-exo-black/60 rounded-full overflow-hidden">
<div
class="h-full bg-exo-yellow rounded-full transition-all duration-150 ease-out"
style="width: {percentage}%"
></div>
</div>
<div class="text-right text-xs text-exo-light-gray/70 mt-0.5 font-mono">
{percentage}%
</div>
</div>
<style>
.prefill-progress {
width: 100%;
}
</style>
@@ -6,8 +6,6 @@
isTopologyMinimized,
debugMode,
nodeThunderboltBridge,
nodeRdmaCtl,
nodeIdentities,
type NodeInfo,
} from "$lib/stores/app.svelte";
@@ -33,8 +31,6 @@
const data = $derived(topologyData());
const debugEnabled = $derived(debugMode());
const tbBridgeData = $derived(nodeThunderboltBridge());
const rdmaCtlData = $derived(nodeRdmaCtl());
const identitiesData = $derived(nodeIdentities());
function getNodeLabel(nodeId: string): string {
const node = data?.nodes?.[nodeId];
@@ -337,27 +333,14 @@
if (edge.source === a) entry.aToB = true;
else entry.bToA = true;
let ip: string;
let ifaceLabel: string;
let missingIface: boolean;
if (edge.sourceRdmaIface || edge.sinkRdmaIface) {
ip = "RDMA";
ifaceLabel = `${edge.sourceRdmaIface || "?"} \u2192 ${edge.sinkRdmaIface || "?"}`;
missingIface = false;
} else {
ip = edge.sendBackIp || "?";
const ifaceInfo = getInterfaceLabel(edge.source, ip);
ifaceLabel = ifaceInfo.label;
missingIface = ifaceInfo.missing;
}
const ip = edge.sendBackIp || "?";
const ifaceInfo = getInterfaceLabel(edge.source, ip);
entry.connections.push({
from: edge.source,
to: edge.target,
ip,
ifaceLabel,
missingIface,
ifaceLabel: ifaceInfo.label,
missingIface: ifaceInfo.missing,
});
pairMap.set(key, entry);
});
@@ -1137,17 +1120,15 @@
.text(` (${ramUsagePercent.toFixed(0)}%)`);
}
// Debug mode: Show TB bridge and RDMA status
// Debug mode: Show TB bridge 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)";
@@ -1155,46 +1136,12 @@
nodeG
.append("text")
.attr("x", nodeInfo.x)
.attr("y", debugLabelY)
.attr("y", tbY)
.attr("text-anchor", "middle")
.attr("fill", tbColor)
.attr("font-size", debugFontSize)
.attr("font-size", tbFontSize)
.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})` : ""}`,
);
}
}
});
-1
View File
@@ -11,5 +11,4 @@ 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 MetaInstanceCard } from "./MetaInstanceCard.svelte";
export { default as ModelPickerModal } from "./ModelPickerModal.svelte";
+35 -353
View File
@@ -49,7 +49,6 @@ export interface NodeInfo {
};
last_macmon_update: number;
friendly_name?: string;
os_version?: string;
}
export interface TopologyEdge {
@@ -57,8 +56,6 @@ export interface TopologyEdge {
target: string;
sendBackIp?: string;
sendBackInterface?: string;
sourceRdmaIface?: string;
sinkRdmaIface?: string;
}
export interface TopologyData {
@@ -72,30 +69,13 @@ export interface Instance {
runnerToShard?: Record<string, unknown>;
nodeToRunner?: Record<string, string>;
};
metaInstanceId?: string | null;
}
export interface MetaInstance {
metaInstanceId: string;
modelId: string;
sharding: "Pipeline" | "Tensor";
instanceMeta: "MlxRing" | "MlxJaccl";
minNodes: number;
nodeIds: string[] | null;
placementError: string | null;
consecutiveFailures: number;
lastFailureError: string | null;
}
export type MetaInstanceStatus = "active" | "provisioning" | "error";
// Granular node state types from the new state structure
interface RawNodeIdentity {
modelId?: string;
chipId?: string;
friendlyName?: string;
osVersion?: string;
osBuildVersion?: string;
}
interface RawMemoryUsage {
@@ -238,7 +218,6 @@ interface RawStateResponse {
MlxJacclInstance?: Instance;
}
>;
metaInstances?: Record<string, MetaInstance>;
runners?: Record<string, unknown>;
downloads?: Record<string, unknown[]>;
// New granular node state fields
@@ -246,19 +225,6 @@ 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,
@@ -289,11 +255,6 @@ export interface TokenData {
topLogprobs: TopLogprob[];
}
export interface PrefillProgress {
processed: number;
total: number;
}
export interface Message {
id: string;
role: "user" | "assistant" | "system";
@@ -317,7 +278,6 @@ export interface Conversation {
modelId: string | null;
sharding: string | null;
instanceType: string | null;
enableThinking: boolean | null;
}
const STORAGE_KEY = "exo-conversations";
@@ -327,14 +287,13 @@ const IMAGE_PARAMS_STORAGE_KEY = "exo-image-generation-params";
export interface ImageGenerationParams {
// Basic params
size:
| "auto"
| "512x512"
| "768x768"
| "1024x1024"
| "1024x768"
| "768x1024"
| "1024x1536"
| "1536x1024";
| "1024x1365"
| "1365x1024";
quality: "low" | "medium" | "high";
outputFormat: "png" | "jpeg";
numImages: number;
@@ -358,7 +317,7 @@ export interface EditingImage {
}
const DEFAULT_IMAGE_PARAMS: ImageGenerationParams = {
size: "auto",
size: "1024x1024",
quality: "medium",
outputFormat: "png",
numImages: 1,
@@ -466,7 +425,6 @@ function transformTopology(
},
last_macmon_update: Date.now() / 1000,
friendly_name: identity?.friendlyName,
os_version: identity?.osVersion,
};
}
@@ -479,8 +437,6 @@ 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) {
@@ -488,23 +444,10 @@ 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,
sourceRdmaIface,
sinkRdmaIface,
});
edges.push({ source, target: sink, sendBackIp });
}
}
}
@@ -541,43 +484,18 @@ class AppStore {
ttftMs = $state<number | null>(null); // Time to first token in ms
tps = $state<number | null>(null); // Tokens per second
totalTokens = $state<number>(0); // Total tokens in current response
prefillProgress = $state<PrefillProgress | null>(null);
// Abort controller for stopping generation
private currentAbortController: AbortController | null = null;
// Topology state
topologyData = $state<TopologyData | null>(null);
instances = $state<Record<string, unknown>>({});
metaInstances = $state<Record<string, MetaInstance>>({});
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,
@@ -633,7 +551,6 @@ class AppStore {
modelId: conversation.modelId ?? null,
sharding: conversation.sharding ?? null,
instanceType: conversation.instanceType ?? null,
enableThinking: conversation.enableThinking ?? null,
}));
}
} catch (error) {
@@ -823,7 +740,6 @@ class AppStore {
modelId: derivedModelId,
sharding: derivedSharding,
instanceType: derivedInstanceType,
enableThinking: null,
};
this.conversations.unshift(conversation);
@@ -849,7 +765,6 @@ 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;
@@ -1285,24 +1200,12 @@ class AppStore {
this.instances = data.instances;
this.refreshConversationModelFromInstances();
}
if (data.metaInstances) {
this.metaInstances = data.metaInstances;
}
if (data.runners) {
this.runners = data.runners;
}
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
@@ -1313,79 +1216,6 @@ class AppStore {
}
}
async createMetaInstance(
modelId: string,
sharding: "Pipeline" | "Tensor" = "Pipeline",
instanceMeta: "MlxRing" | "MlxJaccl" = "MlxRing",
minNodes: number = 1,
nodeIds: string[] | null = null,
) {
try {
const response = await fetch("/meta_instance", {
method: "POST",
headers: { "Content-Type": "application/json" },
body: JSON.stringify({
model_id: modelId,
sharding,
instance_meta: instanceMeta,
min_nodes: minNodes,
node_ids: nodeIds,
}),
});
if (!response.ok) {
console.error("Failed to create meta-instance:", response.status);
}
await this.fetchState();
} catch (error) {
console.error("Error creating meta-instance:", error);
}
}
async deleteMetaInstance(metaInstanceId: string) {
try {
const response = await fetch(`/meta_instance/${metaInstanceId}`, {
method: "DELETE",
headers: { "Content-Type": "application/json" },
});
if (!response.ok) {
console.error("Failed to delete meta-instance:", response.status);
}
await this.fetchState();
} catch (error) {
console.error("Error deleting meta-instance:", error);
}
}
getMetaInstanceStatus(
metaInstance: MetaInstance,
): MetaInstanceStatus {
// Check if any running instance is bound to this meta-instance
for (const instanceWrapper of Object.values(this.instances)) {
if (!instanceWrapper || typeof instanceWrapper !== "object") continue;
const keys = Object.keys(instanceWrapper as Record<string, unknown>);
if (keys.length !== 1) continue;
const inner = (instanceWrapper as Record<string, unknown>)[keys[0]];
if (inner && typeof inner === "object" && (inner as Instance).metaInstanceId === metaInstance.metaInstanceId) {
return "active";
}
}
if (metaInstance.placementError) return "error";
return "provisioning";
}
getMetaInstanceBackingNodes(metaInstance: MetaInstance): string[] {
for (const instanceWrapper of Object.values(this.instances)) {
if (!instanceWrapper || typeof instanceWrapper !== "object") continue;
const keys = Object.keys(instanceWrapper as Record<string, unknown>);
if (keys.length !== 1) continue;
const inner = (instanceWrapper as Record<string, unknown>)[keys[0]] as Instance;
if (inner?.metaInstanceId === metaInstance.metaInstanceId && inner?.shardAssignments?.nodeToRunner) {
return Object.keys(inner.shardAssignments.nodeToRunner);
}
}
return [];
}
async fetchPlacementPreviews(modelId: string, showLoading = true) {
if (!modelId) return;
@@ -1745,12 +1575,11 @@ class AppStore {
if (!reader) throw new Error("No response body");
let fullContent = prefixText;
let streamedThinking = "";
const collectedTokens: TokenData[] = [...tokensToKeep];
interface ChatCompletionChunk {
choices?: Array<{
delta?: { content?: string; reasoning_content?: string };
delta?: { content?: string };
logprobs?: {
content?: Array<{
token: string;
@@ -1771,7 +1600,6 @@ class AppStore {
(parsed) => {
const choice = parsed.choices?.[0];
const delta = choice?.delta?.content;
const thinkingDelta = choice?.delta?.reasoning_content;
// Collect logprobs data
const logprobsContent = choice?.logprobs?.content;
@@ -1790,11 +1618,7 @@ class AppStore {
}
}
if (thinkingDelta) {
streamedThinking += thinkingDelta;
}
if (delta || thinkingDelta) {
if (delta) {
if (firstTokenTime === null) {
firstTokenTime = performance.now();
this.ttftMs = firstTokenTime - requestStartTime;
@@ -1808,14 +1632,9 @@ class AppStore {
this.tps = ((tokenCount - tokensToKeep.length) / elapsed) * 1000;
}
if (delta) {
fullContent += delta;
}
const { displayContent, thinkingContent: tagThinking } =
fullContent += delta;
const { displayContent, thinkingContent } =
this.stripThinkingTags(fullContent);
const combinedThinking = [streamedThinking, tagThinking]
.filter(Boolean)
.join("\n\n");
if (this.activeConversationId === targetConversationId) {
this.currentResponse = displayContent;
@@ -1827,7 +1646,7 @@ class AppStore {
messageId,
(m) => {
m.content = displayContent;
m.thinking = combinedThinking || undefined;
m.thinking = thinkingContent || undefined;
m.tokens = [...collectedTokens];
},
);
@@ -1839,14 +1658,11 @@ class AppStore {
// Final update
if (this.conversationExists(targetConversationId)) {
const { displayContent, thinkingContent: tagThinking } =
const { displayContent, thinkingContent } =
this.stripThinkingTags(fullContent);
const finalThinking = [streamedThinking, tagThinking]
.filter(Boolean)
.join("\n\n");
this.updateConversationMessage(targetConversationId, messageId, (m) => {
m.content = displayContent;
m.thinking = finalThinking || undefined;
m.thinking = thinkingContent || undefined;
m.tokens = [...collectedTokens];
if (this.ttftMs !== null) m.ttftMs = this.ttftMs;
if (this.tps !== null) m.tps = this.tps;
@@ -1954,12 +1770,11 @@ class AppStore {
}
let streamedContent = "";
let streamedThinking = "";
const collectedTokens: TokenData[] = [];
interface ChatCompletionChunk {
choices?: Array<{
delta?: { content?: string; reasoning_content?: string };
delta?: { content?: string };
logprobs?: {
content?: Array<{
token: string;
@@ -1980,7 +1795,6 @@ class AppStore {
(parsed) => {
const choice = parsed.choices?.[0];
const delta = choice?.delta?.content;
const thinkingDelta = choice?.delta?.reasoning_content;
// Collect logprobs data
const logprobsContent = choice?.logprobs?.content;
@@ -1999,19 +1813,10 @@ class AppStore {
}
}
if (thinkingDelta) {
streamedThinking += thinkingDelta;
}
if (delta || thinkingDelta) {
if (delta) {
streamedContent += delta;
}
const { displayContent, thinkingContent: tagThinking } =
if (delta) {
streamedContent += delta;
const { displayContent, thinkingContent } =
this.stripThinkingTags(streamedContent);
const combinedThinking = [streamedThinking, tagThinking]
.filter(Boolean)
.join("\n\n");
// Only update currentResponse if target conversation is active
if (this.activeConversationId === targetConversationId) {
@@ -2024,7 +1829,7 @@ class AppStore {
assistantMessage.id,
(msg) => {
msg.content = displayContent;
msg.thinking = combinedThinking || undefined;
msg.thinking = thinkingContent || undefined;
msg.tokens = [...collectedTokens];
},
);
@@ -2036,17 +1841,14 @@ class AppStore {
// Final cleanup of the message (if conversation still exists)
if (this.conversationExists(targetConversationId)) {
const { displayContent, thinkingContent: tagThinking } =
const { displayContent, thinkingContent } =
this.stripThinkingTags(streamedContent);
const finalThinking = [streamedThinking, tagThinking]
.filter(Boolean)
.join("\n\n");
this.updateConversationMessage(
targetConversationId,
assistantMessage.id,
(msg) => {
msg.content = displayContent;
msg.thinking = finalThinking || undefined;
msg.thinking = thinkingContent || undefined;
msg.tokens = [...collectedTokens];
},
);
@@ -2067,11 +1869,6 @@ class AppStore {
}
}
/**
* Whether thinking is enabled for the current conversation
*/
thinkingEnabled = $state(true);
/**
* Selected model for chat (can be set by the UI)
*/
@@ -2135,7 +1932,6 @@ class AppStore {
reader: ReadableStreamDefaultReader<Uint8Array>,
targetConversationId: string,
onChunk: (parsed: T) => void,
onEvent?: Record<string, (data: unknown) => void>,
): Promise<void> {
const decoder = new TextDecoder();
let buffer = "";
@@ -2156,24 +1952,6 @@ class AppStore {
const trimmed = line.trim();
if (!trimmed) continue;
// Handle SSE comments (": key json") for prefill progress etc.
if (trimmed.startsWith(": ") && onEvent) {
const comment = trimmed.slice(2);
const spaceIdx = comment.indexOf(" ");
if (spaceIdx > 0) {
const key = comment.slice(0, spaceIdx);
if (onEvent[key]) {
try {
const parsed = JSON.parse(comment.slice(spaceIdx + 1));
onEvent[key](parsed);
} catch {
// Skip malformed JSON in comment
}
}
}
continue;
}
if (trimmed.startsWith("data: ")) {
const data = trimmed.slice(6);
if (data === "[DONE]") continue;
@@ -2269,7 +2047,6 @@ class AppStore {
textContent?: string;
preview?: string;
}[],
enableThinking?: boolean | null,
): Promise<void> {
if ((!content.trim() && (!files || files.length === 0)) || this.isLoading)
return;
@@ -2405,9 +2182,6 @@ class AppStore {
let firstTokenTime: number | null = null;
let tokenCount = 0;
const abortController = new AbortController();
this.currentAbortController = abortController;
const response = await fetch("/v1/chat/completions", {
method: "POST",
headers: {
@@ -2420,11 +2194,7 @@ class AppStore {
stream: true,
logprobs: true,
top_logprobs: 5,
...(enableThinking != null && {
enable_thinking: enableThinking,
}),
}),
signal: abortController.signal,
});
if (!response.ok) {
@@ -2438,11 +2208,10 @@ class AppStore {
}
let streamedContent = "";
let streamedThinking = "";
interface ChatCompletionChunk {
choices?: Array<{
delta?: { content?: string; reasoning_content?: string };
delta?: { content?: string };
logprobs?: {
content?: Array<{
token: string;
@@ -2463,14 +2232,8 @@ class AppStore {
reader,
targetConversationId,
(parsed) => {
// Clear prefill progress when first token data arrives
if (this.prefillProgress) {
this.prefillProgress = null;
}
const choice = parsed.choices?.[0];
const tokenContent = choice?.delta?.content;
const thinkingContent = choice?.delta?.reasoning_content;
// Collect logprobs data
const logprobsContent = choice?.logprobs?.content;
@@ -2489,11 +2252,7 @@ class AppStore {
}
}
if (thinkingContent) {
streamedThinking += thinkingContent;
}
if (tokenContent || thinkingContent) {
if (tokenContent) {
// Track first token for TTFT
if (firstTokenTime === null) {
firstTokenTime = performance.now();
@@ -2510,16 +2269,11 @@ class AppStore {
this.tps = (tokenCount / elapsed) * 1000;
}
if (tokenContent) {
streamedContent += tokenContent;
}
streamedContent += tokenContent;
// Use stripThinkingTags as fallback for any <think> tags still in content
const { displayContent, thinkingContent: tagThinking } =
// Strip thinking tags for display and extract thinking content
const { displayContent, thinkingContent } =
this.stripThinkingTags(streamedContent);
const combinedThinking = [streamedThinking, tagThinking]
.filter(Boolean)
.join("\n\n");
// Only update currentResponse if target conversation is active
if (this.activeConversationId === targetConversationId) {
@@ -2532,7 +2286,7 @@ class AppStore {
assistantMessage.id,
(msg) => {
msg.content = displayContent;
msg.thinking = combinedThinking || undefined;
msg.thinking = thinkingContent || undefined;
msg.tokens = [...collectedTokens];
},
);
@@ -2540,26 +2294,8 @@ class AppStore {
this.persistConversation(targetConversationId);
}
},
{
prefill_progress: (data) => {
// TaggedModel wraps as {"PrefillProgressChunk": {...}}
// model_dump_json() uses snake_case (by_alias defaults to False)
const raw = data as Record<string, unknown>;
const inner = (raw["PrefillProgressChunk"] ?? raw) as {
processed_tokens: number;
total_tokens: number;
};
this.prefillProgress = {
processed: inner.processed_tokens,
total: inner.total_tokens,
};
},
},
);
// Clear prefill progress after stream ends
this.prefillProgress = null;
// Calculate final TPS
if (firstTokenTime !== null && tokenCount > 1) {
const totalGenerationTime = performance.now() - firstTokenTime;
@@ -2568,17 +2304,14 @@ class AppStore {
// Final cleanup of the message (if conversation still exists)
if (this.conversationExists(targetConversationId)) {
const { displayContent, thinkingContent: tagThinking } =
const { displayContent, thinkingContent } =
this.stripThinkingTags(streamedContent);
const finalThinking = [streamedThinking, tagThinking]
.filter(Boolean)
.join("\n\n");
this.updateConversationMessage(
targetConversationId,
assistantMessage.id,
(msg) => {
msg.content = displayContent;
msg.thinking = finalThinking || undefined;
msg.thinking = thinkingContent || undefined;
msg.tokens = [...collectedTokens];
// Store performance metrics on the message
if (this.ttftMs !== null) {
@@ -2593,31 +2326,20 @@ class AppStore {
this.persistConversation(targetConversationId);
}
} catch (error) {
if (error instanceof DOMException && error.name === "AbortError") {
// User stopped generation — not an error
} else {
console.error("Error sending message:", error);
this.handleStreamingError(
error,
targetConversationId,
assistantMessage.id,
"Failed to get response",
);
}
console.error("Error sending message:", error);
this.handleStreamingError(
error,
targetConversationId,
assistantMessage.id,
"Failed to get response",
);
} finally {
this.currentAbortController = null;
this.prefillProgress = null;
this.isLoading = false;
this.currentResponse = "";
this.saveConversationsToStorage();
}
}
stopGeneration(): void {
this.currentAbortController?.abort();
this.currentAbortController = null;
}
/**
* Generate an image using the image generation API
*/
@@ -3130,18 +2852,6 @@ 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
*/
@@ -3244,26 +2954,21 @@ export const isLoading = () => appStore.isLoading;
export const ttftMs = () => appStore.ttftMs;
export const tps = () => appStore.tps;
export const totalTokens = () => appStore.totalTokens;
export const prefillProgress = () => appStore.prefillProgress;
export const topologyData = () => appStore.topologyData;
export const instances = () => appStore.instances;
export const metaInstances = () => appStore.metaInstances;
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();
// Actions
export const stopGeneration = () => appStore.stopGeneration();
export const startChat = () => appStore.startChat();
export const sendMessage = (
content: string,
@@ -3274,8 +2979,7 @@ export const sendMessage = (
textContent?: string;
preview?: string;
}[],
enableThinking?: boolean | null,
) => appStore.sendMessage(content, files, enableThinking);
) => appStore.sendMessage(content, files);
export const generateImage = (prompt: string, modelId?: string) =>
appStore.generateImage(prompt, modelId);
export const editImage = (
@@ -3318,8 +3022,6 @@ 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;
@@ -3336,27 +3038,7 @@ export const setChatSidebarVisible = (visible: boolean) =>
appStore.setChatSidebarVisible(visible);
export const refreshState = () => appStore.fetchState();
// Meta-instance actions
export const createMetaInstance = (
modelId: string,
sharding?: "Pipeline" | "Tensor",
instanceMeta?: "MlxRing" | "MlxJaccl",
minNodes?: number,
nodeIds?: string[] | null,
) => appStore.createMetaInstance(modelId, sharding, instanceMeta, minNodes, nodeIds);
export const deleteMetaInstance = (metaInstanceId: string) =>
appStore.deleteMetaInstance(metaInstanceId);
export const getMetaInstanceStatus = (metaInstance: MetaInstance) =>
appStore.getMetaInstanceStatus(metaInstance);
export const getMetaInstanceBackingNodes = (metaInstance: MetaInstance) =>
appStore.getMetaInstanceBackingNodes(metaInstance);
// 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;
// Thunderbolt bridge status
export const thunderboltBridgeCycles = () => appStore.thunderboltBridgeCycles;
export const nodeThunderboltBridge = () => appStore.nodeThunderboltBridge;
@@ -1,75 +0,0 @@
/**
* 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();
File diff suppressed because it is too large Load Diff
File diff suppressed because it is too large Load Diff
+12 -3
View File
@@ -74,6 +74,7 @@
perSystem =
{ config, self', inputs', pkgs, lib, system, ... }:
let
fenixToolchain = inputs'.fenix.packages.complete;
# Use pinned nixpkgs for swift-format (swift is broken on x86_64-linux in newer nixpkgs)
pkgsSwift = import inputs.nixpkgs-swift { inherit system; };
in
@@ -83,7 +84,7 @@
inherit system;
config.allowUnfreePredicate = pkg: (pkg.pname or "") == "metal-toolchain";
overlays = [
(import ./nix/apple-sdk-overlay.nix)
(final: _: { apple-sdk_26 = final.callPackage ./nix/apple-sdk/package.nix { darwinSdkMajorVersion = "26"; }; })
];
};
treefmt = {
@@ -107,14 +108,17 @@
enable = true;
package = pkgsSwift.swiftPackages.swift-format;
};
shfmt.enable = true;
shfmt = {
enable = true;
excludes = [ "nix/apple-sdk/**" ];
};
};
};
packages = lib.optionalAttrs pkgs.stdenv.hostPlatform.isDarwin (
let
uvLock = builtins.fromTOML (builtins.readFile ./uv.lock);
mlxPackage = builtins.head (builtins.filter (p: p.name == "mlx" && p.source ? git) uvLock.package);
mlxPackage = builtins.head (builtins.filter (p: p.name == "mlx") uvLock.package);
uvLockMlxVersion = mlxPackage.version;
in
{
@@ -124,6 +128,11 @@
inherit uvLockMlxVersion;
};
default = self'.packages.exo;
sdk-version = pkgs.runCommand "sdk-version" { } ''
mkdir -p $out
echo ${pkgs.apple-sdk_26.version} > $out/version
'';
}
);
-18
View File
@@ -1,18 +0,0 @@
# 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} $out/metadata/versions.json
'';
in
{
apple-sdk_26 = final.callPackage (patchedSrc + "/package.nix") {
darwinSdkMajorVersion = "26";
};
}
View File
@@ -0,0 +1,48 @@
{ lib
, fetchFromGitHub
, stdenvNoCC
,
}:
let
CoreSymbolication = stdenvNoCC.mkDerivation (finalAttrs: {
pname = "CoreSymbolication";
version = "0-unstable-2018-06-17";
src = fetchFromGitHub {
repo = "CoreSymbolication";
owner = "matthewbauer";
rev = "24c87c23664b3ee05dc7a5a87d647ae476a680e4";
hash = "sha256-PzvLq94eNhP0+rLwGMKcMzxuD6MlrNI7iT/eV0obtSE=";
};
patches = [
# Add missing symbol definitions needed to build `zlog` in system_cmds.
# https://github.com/matthewbauer/CoreSymbolication/pull/2
../patches/0001-Add-function-definitions-needed-to-build-zlog-in-sys.patch
../patches/0002-Add-CF_EXPORT-To-const-symbols.patch
];
dontBuild = true;
installPhase = ''
mkdir -p "$out/include"
cp *.h "$out/include"
'';
meta = {
description = "Reverse engineered headers for Apple's CoreSymbolication framework";
homepage = "https://github.com/matthewbauer/CoreSymbolication";
license = lib.licenses.mit;
teams = [ lib.teams.darwin ];
platforms = lib.platforms.darwin;
};
});
in
self: super: {
buildPhase = super.buildPhase or "" + ''
mkdir -p System/Library/PrivateFrameworks/CoreSymbolication.framework/Versions/A/Headers
ln -s Versions/Current/Headers System/Library/PrivateFrameworks/CoreSymbolication.framework/Headers
cp '${CoreSymbolication}/include/'*.h System/Library/PrivateFrameworks/CoreSymbolication.framework/Versions/A/Headers
'';
}
@@ -0,0 +1,13 @@
{ lib, config }:
self: super: {
preBuild = super.preBuild or "" + ''
platformPath=$out/Platforms/MacOSX.platform
sdkpath=$platformPath/Developer/SDKs
'';
preInstall = super.preInstall or "" + ''
platformPath=$out/Platforms/MacOSX.platform
sdkpath=$platformPath/Developer/SDKs
'';
}
+38
View File
@@ -0,0 +1,38 @@
{ lib
, fetchurl
, cpio
, pbzx
,
}:
{ urls
, version
, hash
,
}:
fetchurl {
pname = "macOS-SDK";
inherit version urls hash;
recursiveHash = true;
nativeBuildInputs = [
cpio
pbzx
];
postFetch = ''
renamed=$(mktemp -d)/sdk.xar
mv "$downloadedFile" "$renamed"
pbzx "$renamed" | cpio -idm
src=Library/Developer/CommandLineTools/SDKs/MacOSX${lib.versions.majorMinor version}.sdk
# Remove unwanted binaries, man pages, and folders from the SDK.
rm -rf $src/usr/bin $src/usr/share $src/System/Library/Perl
mkdir -p "$out"
cp -rd $src/* "$out"
'';
}
@@ -0,0 +1,10 @@
{ makeSetupHook, sdkVersion }:
self: super: {
passthru = super.passthru or { } // {
privateFrameworksHook = makeSetupHook
{
name = "apple-sdk-private-frameworks-hook";
} ../setup-hooks/add-private-frameworks.sh;
};
}
@@ -0,0 +1,38 @@
let
lockfile = builtins.fromJSON (builtins.readFile ../metadata/apple-oss-lockfile.json);
in
{ lib
, fetchFromGitHub
, stdenvNoCC
, sdkVersion
,
}:
let
sdkinfo = lockfile.${sdkVersion};
in
self: super: {
passthru = super.passthru or { } // {
# Returns the raw source from apple-oss-distributions repo.
# This is mostly useful for copying private headers needed to build other source releases.
#
# Note: The source releases are mostly not used to build the SDK. Unless they can be used to build binaries,
# theyre not used.
sourceRelease =
name:
let
lockinfo = sdkinfo.${name};
in
fetchFromGitHub
{
owner = "apple-oss-distributions";
repo = name;
rev = lockinfo.rev or "${name}-${lockinfo.version}";
inherit (lockinfo) hash;
}
// {
inherit (lockinfo) version;
};
};
}
+327
View File
@@ -0,0 +1,327 @@
{ lib
, stdenvNoCC
, xcodePlatform
, sdkVersion
,
}:
let
inherit (lib.generators) toPlist;
Info = rec {
CFBundleIdentifier = "com.apple.platform.${Name}";
DefaultProperties = {
COMPRESS_PNG_FILES = "NO";
DEPLOYMENT_TARGET_SETTING_NAME = stdenvNoCC.hostPlatform.darwinMinVersionVariable;
STRIP_PNG_TEXT = "NO";
};
Description = if stdenvNoCC.hostPlatform.isMacOS then "macOS" else "iOS";
FamilyIdentifier = lib.toLower xcodePlatform;
FamilyName = Description;
Identifier = CFBundleIdentifier;
MinimumSDKVersion = stdenvNoCC.hostPlatform.darwinMinVersion;
Name = lib.toLower xcodePlatform;
Type = "Platform";
Version = sdkVersion;
};
# These files are all based off of Xcode spec files found in
# /Applications/Xcode.app/Contents/Developer/Platforms/MacOSX.platform/Developer/Library/Xcode/PrivatePlugIns/IDEOSXSupportCore.ideplugin/Contents/Resources.
# Based off of the "MacOSX Architectures.xcspec" file. All i386 stuff
# is removed because NixPkgs only supports darwin-x86_64 and darwin-arm64.
Architectures = [
{
Identifier = "Standard";
Type = "Architecture";
Name = "Standard Architectures (Apple Silicon, 64-bit Intel)";
RealArchitectures = [
"arm64"
"x86_64"
];
ArchitectureSetting = "ARCHS_STANDARD";
}
{
Identifier = "Universal";
Type = "Architecture";
Name = "Universal (Apple Silicon, 64-bit Intel)";
RealArchitectures = [
"arm64"
"x86_64"
];
ArchitectureSetting = "ARCHS_STANDARD_32_64_BIT";
}
{
Identifier = "Native";
Type = "Architecture";
Name = "Native Architecture of Build Machine";
ArchitectureSetting = "NATIVE_ARCH_ACTUAL";
}
{
Identifier = "Standard64bit";
Type = "Architecture";
Name = "Apple Silicon, 64-bit Intel";
RealArchitectures = [
"arm64"
"x86_64"
];
ArchitectureSetting = "ARCHS_STANDARD_64_BIT";
}
{
Identifier = stdenvNoCC.hostPlatform.darwinArch;
Type = "Architecture";
Name = "Apple Silicon or Intel 64-bit";
}
{
Identifier = "Standard_Including_64_bit";
Type = "Architecture";
Name = "Standard Architectures (including 64-bit)";
RealArchitectures = [
"arm64"
"x86_64"
];
ArchitectureSetting = "ARCHS_STANDARD_INCLUDING_64_BIT";
}
];
# Based off of the "MacOSX Package Types.xcspec" file. Only keep the
# bare minimum needed.
PackageTypes = [
{
Identifier = "com.apple.package-type.mach-o-executable";
Type = "PackageType";
Name = "Mach-O Executable";
DefaultBuildSettings = {
EXECUTABLE_NAME = "$(EXECUTABLE_PREFIX)$(PRODUCT_NAME)$(EXECUTABLE_VARIANT_SUFFIX)$(EXECUTABLE_SUFFIX)";
EXECUTABLE_PATH = "$(EXECUTABLE_NAME)";
};
ProductReference = {
FileType = "compiled.mach-o.executable";
Name = "$(EXECUTABLE_NAME)";
};
}
{
Identifier = "com.apple.package-type.mach-o-objfile";
Type = "PackageType";
Name = "Mach-O Object File";
DefaultBuildSettings = {
EXECUTABLE_NAME = "$(EXECUTABLE_PREFIX)$(PRODUCT_NAME)$(EXECUTABLE_VARIANT_SUFFIX)$(EXECUTABLE_SUFFIX)";
EXECUTABLE_PATH = "$(EXECUTABLE_NAME)";
};
ProductReference = {
FileType = "compiled.mach-o.objfile";
Name = "$(EXECUTABLE_NAME)";
};
}
{
Identifier = "com.apple.package-type.mach-o-dylib";
Type = "PackageType";
Name = "Mach-O Dynamic Library";
DefaultBuildSettings = {
EXECUTABLE_NAME = "$(EXECUTABLE_PREFIX)$(PRODUCT_NAME)$(EXECUTABLE_VARIANT_SUFFIX)$(EXECUTABLE_SUFFIX)";
EXECUTABLE_PATH = "$(EXECUTABLE_NAME)";
};
ProductReference = {
FileType = "compiled.mach-o.dylib";
Name = "$(EXECUTABLE_NAME)";
};
}
{
Identifier = "com.apple.package-type.static-library";
Type = "PackageType";
Name = "Mach-O Static Library";
DefaultBuildSettings = {
EXECUTABLE_PREFIX = "lib";
EXECUTABLE_SUFFIX = ".a";
EXECUTABLE_NAME = "$(EXECUTABLE_PREFIX)$(PRODUCT_NAME)$(EXECUTABLE_VARIANT_SUFFIX)$(EXECUTABLE_SUFFIX)";
EXECUTABLE_PATH = "$(EXECUTABLE_NAME)";
};
ProductReference = {
FileType = "archive.ar";
Name = "$(EXECUTABLE_NAME)";
IsLaunchable = "NO";
};
}
{
Identifier = "com.apple.package-type.wrapper";
Type = "PackageType";
Name = "Wrapper";
DefaultBuildSettings = {
WRAPPER_SUFFIX = ".bundle";
WRAPPER_NAME = "$(WRAPPER_PREFIX)$(PRODUCT_NAME)$(WRAPPER_SUFFIX)";
CONTENTS_FOLDER_PATH = "$(WRAPPER_NAME)/Contents";
EXECUTABLE_NAME = "$(EXECUTABLE_PREFIX)$(PRODUCT_NAME)$(EXECUTABLE_VARIANT_SUFFIX)$(EXECUTABLE_SUFFIX)";
EXECUTABLE_FOLDER_PATH = "$(CONTENTS_FOLDER_PATH)/MacOS";
EXECUTABLE_PATH = "$(EXECUTABLE_FOLDER_PATH)/$(EXECUTABLE_NAME)";
INFOPLIST_PATH = "$(CONTENTS_FOLDER_PATH)/Info.plist";
INFOSTRINGS_PATH = "$(LOCALIZED_RESOURCES_FOLDER_PATH)/InfoPlist.strings";
PKGINFO_PATH = "$(CONTENTS_FOLDER_PATH)/PkgInfo";
PBDEVELOPMENTPLIST_PATH = "$(CONTENTS_FOLDER_PATH)/pbdevelopment.plist";
VERSIONPLIST_PATH = "$(CONTENTS_FOLDER_PATH)/version.plist";
PUBLIC_HEADERS_FOLDER_PATH = "$(CONTENTS_FOLDER_PATH)/Headers";
PRIVATE_HEADERS_FOLDER_PATH = "$(CONTENTS_FOLDER_PATH)/PrivateHeaders";
EXECUTABLES_FOLDER_PATH = "$(CONTENTS_FOLDER_PATH)/Executables";
FRAMEWORKS_FOLDER_PATH = "$(CONTENTS_FOLDER_PATH)/Frameworks";
SHARED_FRAMEWORKS_FOLDER_PATH = "$(CONTENTS_FOLDER_PATH)/SharedFrameworks";
SHARED_SUPPORT_FOLDER_PATH = "$(CONTENTS_FOLDER_PATH)/SharedSupport";
UNLOCALIZED_RESOURCES_FOLDER_PATH = "$(CONTENTS_FOLDER_PATH)/Resources";
LOCALIZED_RESOURCES_FOLDER_PATH = "$(UNLOCALIZED_RESOURCES_FOLDER_PATH)/$(DEVELOPMENT_LANGUAGE).lproj";
DOCUMENTATION_FOLDER_PATH = "$(LOCALIZED_RESOURCES_FOLDER_PATH)/Documentation";
PLUGINS_FOLDER_PATH = "$(CONTENTS_FOLDER_PATH)/PlugIns";
SCRIPTS_FOLDER_PATH = "$(UNLOCALIZED_RESOURCES_FOLDER_PATH)/Scripts";
};
ProductReference = {
FileType = "wrapper.cfbundle";
Name = "$(WRAPPER_NAME)";
IsLaunchable = "NO";
};
}
{
Identifier = "com.apple.package-type.wrapper.application";
Type = "PackageType";
BasedOn = "com.apple.package-type.wrapper";
Name = "Application Wrapper";
DefaultBuildSettings = {
GENERATE_PKGINFO_FILE = "YES";
};
ProductReference = {
FileType = "wrapper.application";
Name = "$(WRAPPER_NAME)";
IsLaunchable = "YES";
};
}
];
# Based off of the "MacOSX Product Types.xcspec" file. All
# bundles/wrapper are removed, because we prefer dynamic products in
# NixPkgs.
ProductTypes = [
{
Identifier = "com.apple.product-type.tool";
Type = "ProductType";
Name = "Command-line Tool";
PackageTypes = [ "com.apple.package-type.mach-o-executable" ];
}
{
Identifier = "com.apple.product-type.objfile";
Type = "ProductType";
Name = "Object File";
PackageTypes = [ "com.apple.package-type.mach-o-objfile" ];
}
{
Identifier = "com.apple.product-type.library.dynamic";
Type = "ProductType";
Name = "Dynamic Library";
PackageTypes = [ "com.apple.package-type.mach-o-dylib" ];
DefaultBuildProperties = {
FULL_PRODUCT_NAME = "$(EXECUTABLE_NAME)";
MACH_O_TYPE = "mh_dylib";
REZ_EXECUTABLE = "YES";
EXECUTABLE_SUFFIX = ".$(EXECUTABLE_EXTENSION)";
EXECUTABLE_EXTENSION = "dylib";
DYLIB_COMPATIBILITY_VERSION = "1";
DYLIB_CURRENT_VERSION = "1";
FRAMEWORK_FLAG_PREFIX = "-framework";
LIBRARY_FLAG_PREFIX = "-l";
LIBRARY_FLAG_NOSPACE = "YES";
STRIP_STYLE = "debugging";
GCC_INLINES_ARE_PRIVATE_EXTERN = "YES";
CODE_SIGNING_ALLOWED = "YES";
CODE_SIGNING_REQUIRED = "NO";
};
}
{
Identifier = "com.apple.product-type.library.static";
Type = "ProductType";
Name = "Static Library";
PackageTypes = [ "com.apple.package-type.static-library" ];
DefaultBuildProperties = {
FULL_PRODUCT_NAME = "$(EXECUTABLE_NAME)";
MACH_O_TYPE = "staticlib";
REZ_EXECUTABLE = "YES";
EXECUTABLE_PREFIX = "lib";
EXECUTABLE_SUFFIX = ".$(EXECUTABLE_EXTENSION)";
EXECUTABLE_EXTENSION = "a";
FRAMEWORK_FLAG_PREFIX = "-framework";
LIBRARY_FLAG_PREFIX = "-l";
LIBRARY_FLAG_NOSPACE = "YES";
STRIP_STYLE = "debugging";
SEPARATE_STRIP = "YES";
CLANG_ENABLE_MODULE_DEBUGGING = "NO";
};
}
{
Type = "ProductType";
Identifier = "com.apple.product-type.bundle";
Name = "Bundle";
DefaultBuildProperties = {
FULL_PRODUCT_NAME = "$(WRAPPER_NAME)";
MACH_O_TYPE = "mh_bundle";
WRAPPER_PREFIX = "";
WRAPPER_SUFFIX = ".$(WRAPPER_EXTENSION)";
WRAPPER_EXTENSION = "bundle";
WRAPPER_NAME = "$(WRAPPER_PREFIX)$(PRODUCT_NAME)$(WRAPPER_SUFFIX)";
FRAMEWORK_FLAG_PREFIX = "-framework";
LIBRARY_FLAG_PREFIX = "-l";
LIBRARY_FLAG_NOSPACE = "YES";
STRIP_STYLE = "non-global";
};
PackageTypes = [ "com.apple.package-type.wrapper" ];
IsWrapper = "YES";
HasInfoPlist = "YES";
HasInfoPlistStrings = "YES";
}
{
Identifier = "com.apple.product-type.application";
Type = "ProductType";
BasedOn = "com.apple.product-type.bundle";
Name = "Application";
DefaultBuildProperties = {
MACH_O_TYPE = "mh_execute";
WRAPPER_SUFFIX = ".$(WRAPPER_EXTENSION)";
WRAPPER_EXTENSION = "app";
};
PackageTypes = [ "com.apple.package-type.wrapper.application" ];
}
{
Type = "ProductType";
Identifier = "com.apple.product-type.framework";
Name = "Bundle";
DefaultBuildProperties = {
FULL_PRODUCT_NAME = "$(WRAPPER_NAME)";
MACH_O_TYPE = "mh_bundle";
WRAPPER_PREFIX = "";
WRAPPER_SUFFIX = ".$(WRAPPER_EXTENSION)";
WRAPPER_EXTENSION = "bundle";
WRAPPER_NAME = "$(WRAPPER_PREFIX)$(PRODUCT_NAME)$(WRAPPER_SUFFIX)";
FRAMEWORK_FLAG_PREFIX = "-framework";
LIBRARY_FLAG_PREFIX = "-l";
LIBRARY_FLAG_NOSPACE = "YES";
STRIP_STYLE = "non-global";
};
PackageTypes = [ "com.apple.package-type.wrapper" ];
IsWrapper = "YES";
HasInfoPlist = "YES";
HasInfoPlistStrings = "YES";
}
];
ToolchainInfo = {
Identifier = "com.apple.dt.toolchain.XcodeDefault";
};
in
{
"Info.plist" = builtins.toFile "Info.plist" (toPlist { escape = true; } Info);
"ToolchainInfo.plist" = builtins.toFile "ToolchainInfo.plist" (
toPlist { escape = true; } ToolchainInfo
);
"Architectures.xcspec" = builtins.toFile "Architectures.xcspec" (
toPlist { escape = true; } Architectures
);
"PackageTypes.xcspec" = builtins.toFile "PackageTypes.xcspec" (
toPlist { escape = true; } PackageTypes
);
"ProductTypes.xcspec" = builtins.toFile "ProductTypes.xcspec" (
toPlist { escape = true; } ProductTypes
);
}
+40
View File
@@ -0,0 +1,40 @@
let
removedDylibs = [
# corecrypto is available under a very restrictive license (effectively: non-free, cant use).
# Without the headers and not being able to use corecrypto due to its license, its not very useful.
# Stubs are included in the SDK for all dylibs, including corecrypto. They should be removed.
"/usr/lib/system/libcorecrypto.dylib"
];
in
{ lib
, jq
, llvm
,
}:
self: super: {
nativeBuildInputs = super.nativeBuildInputs or [ ] ++ [
jq
llvm
];
buildPhase = super.buildPhase or "" + ''
echo "Removing the following dylibs from the libSystem reexported libraries list: ${lib.escapeShellArg (lib.concatStringsSep ", " removedDylibs)}"
for libSystem in libSystem.B.tbd libSystem.B_asan.tbd; do
# tbd-v5 is a JSON-based format, which can be manipulated by `jq`.
llvm-readtapi --filetype=tbd-v5 usr/lib/$libSystem \
| jq --argjson libs ${lib.escapeShellArg (builtins.toJSON removedDylibs)} '
if .libraries then
.libraries[] |= select(.install_names[] | any([.] | inside($libs)) | not)
else
.
end
| .main_library.reexported_libraries[].names[] |= select([.] | inside($libs) | not)
' > usr/lib/$libSystem~
# Convert libSystem back to tbd-v4 because not all tooling supports the JSON-based format yet.
llvm-readtapi --filetype=tbd-v4 usr/lib/$libSystem~ -o usr/lib/$libSystem
rm usr/lib/$libSystem~
done
'';
}
+74
View File
@@ -0,0 +1,74 @@
{ lib
, cups
, darwin
, db
, libiconv
, ncurses
, stdenv
, stdenvNoCC
, xcbuild
,
}:
let
# CUPS has too many dependencies to build as part of the Darwin bootstrap. Its also typically taken as an explicit
# dependency by other packages, so building only the headers (to satisfy other SDK headers) should be okay.
cupsHeaders = darwin.bootstrapStdenv.mkDerivation {
pname = "${lib.getName cups}-headers";
version = lib.getVersion cups;
inherit (cups) src;
patches = cups.patches or [ ];
strictDeps = true;
dontBuild = true;
buildInputs = [ darwin.libresolv ]; # The `configure` script requires libresolv headers.
# CUPSs configure script fails to find `ar` when cross-compiling.
configureFlags = [ "ac_cv_path_AR=${stdenv.cc.targetPrefix}ar" ];
installTargets = [ "install-headers" ];
__structuredAttrs = true;
meta = {
inherit (cups.meta)
homepage
description
license
maintainers
platforms
;
};
};
in
self: super: {
# These packages are propagated only because other platforms include them in their libc (or otherwise by default).
# Reducing the number of special cases required to support Darwin makes supporting it easier for package authors.
propagatedBuildInputs =
super.propagatedBuildInputs or [ ]
++ [
libiconv
darwin.libresolv
darwin.libsbuf
# Shipped with the SDK only as a library with no headers
(lib.getLib darwin.libutil)
]
# x86_64-darwin links the object files from Csu when targeting very old releases
++ lib.optionals stdenvNoCC.hostPlatform.isx86_64 [ darwin.Csu ];
# The Darwin module for Swift requires certain headers to be included in the SDK (and not just be propagated).
buildPhase = super.buildPhase or "" + ''
for header in '${lib.getDev libiconv}/include/'* '${lib.getDev ncurses}/include/'* '${cupsHeaders}/include/'*; do
ln -s "$header" "usr/include/$(basename "$header")"
done
'';
# Exported to allow the headers to pass the requisites check in the stdenv bootstrap.
passthru = (super.passthru or { }) // {
cups-headers = cupsHeaders;
};
}
+53
View File
@@ -0,0 +1,53 @@
{ lib
, pkgsBuildHost
, stdenv
, stdenvNoCC
, sdkVersion
,
}:
let
plists = import ./plists.nix {
inherit lib stdenvNoCC sdkVersion;
xcodePlatform = if stdenvNoCC.hostPlatform.isMacOS then "MacOSX" else "iPhoneOS";
};
inherit (pkgsBuildHost) darwin cctools xcbuild;
in
self: super: {
propagatedNativeBuildInputs = super.propagatedNativeBuildInputs or [ ] ++ [ xcbuild.xcrun ];
postInstall = super.postInstall or "" + ''
specspath=$out/Library/Xcode/Specifications
toolchainsPath=$out/Toolchains/XcodeDefault.xctoolchain
mkdir -p "$specspath" "$toolchainsPath"
# xcbuild expects to find things relative to the plist locations. If these are linked instead of copied,
# it wont find any platforms or SDKs.
cp '${plists."Info.plist"}' "$platformPath/Info.plist"
cp '${plists."ToolchainInfo.plist"}' "$toolchainsPath/ToolchainInfo.plist"
for spec in '${xcbuild}/Library/Xcode/Specifications/'*; do
ln -s "$spec" "$specspath/$(basename "$spec")"
done
cp '${plists."Architectures.xcspec"}' "$specspath/Architectures.xcspec"
cp '${plists."PackageTypes.xcspec"}' "$specspath/PackageTypes.xcspec"
cp '${plists."ProductTypes.xcspec"}' "$specspath/ProductTypes.xcspec"
mkdir -p "$out/usr/bin"
ln -s '${xcbuild.xcrun}/bin/xcrun' "$out/usr/bin/xcrun"
# Include `libtool` in the toolchain, so `xcrun -find libtool` can find it without requiring `cctools.libtool`
# as a `nativeBuildInput`.
mkdir -p "$toolchainsPath/usr/bin"
if [ -e '${cctools.libtool}/bin/${stdenv.cc.targetPrefix}libtool' ]; then
ln -s '${cctools.libtool}/bin/${stdenv.cc.targetPrefix}libtool' "$toolchainsPath/usr/bin/libtool"
fi
# Include additional binutils required by some packages (such as Chromium).
for tool in lipo nm otool size strip; do
if [ -e '${darwin.binutils-unwrapped}/bin/${stdenv.cc.targetPrefix}'$tool ]; then
ln -s '${darwin.binutils-unwrapped}/bin/${stdenv.cc.targetPrefix}'$tool "$toolchainsPath/usr/bin/$tool"
fi
done
'';
}
@@ -0,0 +1,24 @@
let
disallowedPackages = builtins.fromJSON (builtins.readFile ../metadata/disallowed-packages.json);
in
{ lib
, jq
, stdenv
,
}:
self: super: {
# Remove headers and stubs for packages that are available in nixpkgs.
buildPhase = super.buildPhase or "" + ''
${lib.concatMapStringsSep "\n" (
pkg:
lib.concatLines (
[ ''echo "Removing headers and libraries from ${pkg.package}"'' ]
++ (map (header: "rm -rf -- usr/include/${header}") pkg.headers or [ ])
++ (map (framework: "rm -rf -- System/Library/Frameworks/${framework}") pkg.frameworks or [ ])
++ (map (library: "rm -rf -- usr/lib/${library}") pkg.libraries or [ ])
)
) disallowedPackages}
'';
}
@@ -0,0 +1,9 @@
{}:
self: super: {
buildPhase = ''
runHook preBuild
${super.buildPhase or ""}
runHook postBuild
'';
}
@@ -0,0 +1,536 @@
{
"14.4": {
"CarbonHeaders": {
"hash": "sha256-nIPXnLr21yVnpBhx9K5q3l/nPARA6JL/dED08MeyhP8=",
"version": "18.1"
},
"CommonCrypto": {
"hash": "sha256-/VoOR9wJuKnmGE1CWGGXxX8SpmALHnEooNTa3QM+ITc=",
"version": "600028.100.1"
},
"IOAudioFamily": {
"hash": "sha256-VSk3jvsITJugtL67Qt0m4qJ879i7Fj6B/NGBFVCwpiU=",
"version": "540.3"
},
"IOBDStorageFamily": {
"hash": "sha256-UgLMsQBe1QLzlbScmPmASBN7VH4YBmNOUX2CEDezjmE=",
"version": "22"
},
"IOCDStorageFamily": {
"hash": "sha256-p/2qM5zjXFDRb/DISpEHxQEdvmuLlRGt/Ygc71Yu2rI=",
"version": "61"
},
"IODVDStorageFamily": {
"hash": "sha256-1Sa8aZBGNtqJBNHva+YXxET6Wcdm2PgVrTzYT/8qrN4=",
"version": "45"
},
"IOFWDVComponents": {
"hash": "sha256-WkfkWnzRupEh20U7vjsTta89clhus6GTkOpXQWXw/bM=",
"version": "208"
},
"IOFireWireAVC": {
"hash": "sha256-IUytBKhhCgg0vtI+7q8d5kxpOUgO3tQD7TMy++jrorc=",
"version": "431"
},
"IOFireWireFamily": {
"hash": "sha256-W0KOF4hkA7kFOnL1ThAeFU/YlhFVqoqk9uzGjcBppX8=",
"version": "487"
},
"IOFireWireSBP2": {
"hash": "sha256-bItnRQIaGUxMyiU0q+4N8e5+jYiDEOUPmsrKhBFXvok=",
"version": "445"
},
"IOFireWireSerialBusProtocolTransport": {
"hash": "sha256-P7egeaD9SSa+YyrIRzM44gILKbIL7vezXK3M6q3MBOI=",
"version": "260"
},
"IOGraphics": {
"hash": "sha256-Ag37fd3tZJLXLVq1yzHOCWGOYYfwwTkC8hnvNaTEaWg=",
"version": "598"
},
"IOHIDFamily": {
"hash": "sha256-fmYTJsquAOBwzsgRmqPyjSJJi1hGcfnMmqLIcTe8W1s=",
"version": "2031.100.16"
},
"IOKitUser": {
"hash": "sha256-1bqRiLvyr2GQfbWwhXHXXIOtIka9YDw5GbKV6bd2k4k=",
"version": "100076.101.1"
},
"IONetworkingFamily": {
"hash": "sha256-J3cLeWKrQ8ypIaqgwRH9eU5JbjEDBVoezj3a2Lvwu5k=",
"version": "177"
},
"IOSerialFamily": {
"hash": "sha256-wVS4QTx6MBOS0VrwyCZ3s5Usezwaf8rWzmNnfdDTXTU=",
"version": "93"
},
"IOStorageFamily": {
"hash": "sha256-cllpJX11c3CX8zEYdOT2TC63sx7NUAHh33yRHhrG2Ro=",
"version": "315"
},
"IOUSBFamily": {
"hash": "sha256-Z0E3TfKP49toYo1Fo9kElRap8CZ+mVDHy5RIexgJTpA=",
"version": "630.4.5"
},
"Libc": {
"hash": "sha256-fxBM4KbPwQNVEJl7PCKP+1nUk9Oce/O2+0lVBxyngew=",
"version": "1592.100.35"
},
"Libinfo": {
"hash": "sha256-zZr6Mmou8Q+G6/wS+k0k7R+XirB94TNCUGS5dhi96ZE=",
"version": "583.0.1"
},
"Libm": {
"hash": "sha256-p4BndAag9d0XSMYWQ+c4myGv5qXbKx5E1VghudSbpTk=",
"version": "2026"
},
"Libnotify": {
"hash": "sha256-7X+6S3C7ZOTXJUeDXOOg5EmoZyLZvtE06x3Is0TGgSU=",
"version": "317.100.2"
},
"Librpcsvc": {
"hash": "sha256-UWYdCQ9QsBqwM01bWr+igINAHSdSluB/FrOclC5AjTI=",
"version": "31"
},
"Libsystem": {
"hash": "sha256-HsItciWrwyXujQ2hwqzv0JKOkkuynXYIqejLAEPJbMc=",
"version": "1345.100.2"
},
"OpenDirectory": {
"hash": "sha256-6fSl8PasCZSBfe0ftaePcBuSEO3syb6kK+mfDI6iR7A=",
"version": "146"
},
"Security": {
"hash": "sha256-NgTGbaw5JkpboDQpt1fSgUr9NYGS+bIOrEMQX7mLAME=",
"version": "61123.100.169"
},
"architecture": {
"hash": "sha256-PRNUrhzSOrwmxSPkKmV0LV7yEIik65sdkfKdBqcwFhU=",
"version": "282"
},
"configd": {
"hash": "sha256-+3xesYxqfsNjWCW3T87OA7+Z1hBqmGEh/I8kP8Ajbso=",
"version": "1300.100.9"
},
"copyfile": {
"hash": "sha256-rSCTgzdHr7QmnPk9rJ9P4fOAolnEQv8PHfgAY+qA0s4=",
"version": "196.100.4"
},
"dtrace": {
"hash": "sha256-04Q35rCKnM5Csv5poFJKpK0VplWq4hvy251/Cb2Kl80=",
"version": "401.100.3"
},
"dyld": {
"hash": "sha256-6P/Da6xP19vmaCROoYv9pl7DaW3/U+qZBJT8PD33bn0=",
"version": "1160.6"
},
"eap8021x": {
"hash": "sha256-Ky6KSlJhyX1NRufGhVBcp+ZFmqYrAxwC/5QvJhC2PhU=",
"version": "354.100.3"
},
"hfs": {
"hash": "sha256-+YUVOttZU7C8I14CC6t3ZH2KxAjjTA2nB0y5bPgLxZM=",
"version": "650.0.2"
},
"launchd": {
"hash": "sha256-8mW9bnuHmRXCx9py8Wy28C5b2QPICW0rlAps5njYa00=",
"version": "842.1.4"
},
"libclosure": {
"hash": "sha256-M/jnIHzKYvdFCO0tJ1JXiD/UcZtJhLIoulaCQQUbn30=",
"version": "90"
},
"libdispatch": {
"hash": "sha256-igqIA5DMVHjG30WMHZZpYY7LRM9hZyMWItD+UxeTehY=",
"version": "1477.100.9"
},
"libmalloc": {
"hash": "sha256-Sh4/z7lGWRMldOPURkP5vLOAb5Ou6AUsVJEWz9wk9hI=",
"version": "521.100.59"
},
"libplatform": {
"hash": "sha256-gojt3sWOr7XO2yYI/B1CmNLTPFieSfoNtlOgQahOCok=",
"version": "316.100.10"
},
"libpthread": {
"hash": "sha256-phjfN8+IU8ibPsflR6LktnSi3giy89ghI+cFyrhiQNo=",
"version": "519.101.1"
},
"mDNSResponder": {
"hash": "sha256-0ECbWeMnIRTsi03BeBEe5boyR/84JJPbxzPQze8hHSA=",
"version": "2200.100.94.0.2"
},
"objc4": {
"hash": "sha256-eUVSpbyTEOMEdHoxSv6lZIZwB+cW/YWIaTZTcHgGOjo=",
"version": "912.3"
},
"ppp": {
"hash": "sha256-8+QUA79sHf85yvGSPE9qCmGsrZDT3NZnbgZVroJw/Hg=",
"version": "1016"
},
"removefile": {
"hash": "sha256-L6I0u8S3h3uV1veKA5HvkSebbBCd78ymlf//KWbebZo=",
"version": "70.100.4"
},
"xnu": {
"hash": "sha256-j5Ep1RX5DTJqTGszrF4d/JtzUqZ6nA6XoExqcIQ0RVQ=",
"version": "10063.101.15"
}
},
"15.5": {
"CarbonHeaders": {
"hash": "sha256-nIPXnLr21yVnpBhx9K5q3l/nPARA6JL/dED08MeyhP8=",
"version": "18.1"
},
"CommonCrypto": {
"hash": "sha256-+qAwL6+s7di9cX/qXtapLkjCFoDuZaSYltRJEG4qekM=",
"version": "600035"
},
"IOAudioFamily": {
"hash": "sha256-VSk3jvsITJugtL67Qt0m4qJ879i7Fj6B/NGBFVCwpiU=",
"version": "600.2"
},
"IOBDStorageFamily": {
"hash": "sha256-s8hTwX0jq2iPULfBLUwpzqtszWuvJrrLGbmrKa/fY4U=",
"version": "24"
},
"IOCDStorageFamily": {
"hash": "sha256-p/2qM5zjXFDRb/DISpEHxQEdvmuLlRGt/Ygc71Yu2rI=",
"version": "62"
},
"IODVDStorageFamily": {
"hash": "sha256-1Sa8aZBGNtqJBNHva+YXxET6Wcdm2PgVrTzYT/8qrN4=",
"version": "46"
},
"IOFWDVComponents": {
"hash": "sha256-WkfkWnzRupEh20U7vjsTta89clhus6GTkOpXQWXw/bM=",
"version": "208"
},
"IOFireWireAVC": {
"hash": "sha256-qR9lSTa7PN5Z9Nis4tfuXlcZGMIU48dete/NPD0UBbE=",
"version": "434"
},
"IOFireWireFamily": {
"hash": "sha256-hmErAXjLWIelqJaCrB8J4IiIxyB7S6EHFY+AY9YhmKQ=",
"version": "490"
},
"IOFireWireSBP2": {
"hash": "sha256-Xk+PDnUaO9q46nQwHwTKf/QXtGclfs0wTWiUbcV7e4s=",
"version": "452"
},
"IOFireWireSerialBusProtocolTransport": {
"hash": "sha256-P7egeaD9SSa+YyrIRzM44gILKbIL7vezXK3M6q3MBOI=",
"version": "261"
},
"IOGraphics": {
"hash": "sha256-iysZE42mOKZbFxSZBNspaBTCRKEKK38DFGBxZWQxZxI=",
"version": "599"
},
"IOHIDFamily": {
"hash": "sha256-gEYPyjXgQ2ABGufCKPjmzMdNRLxhELkCvOURCokyTO4=",
"version": "2115.100.21"
},
"IOKitUser": {
"hash": "sha256-p32U+jHfwA/tqnjF4p1BmojghEXK8KxiflW3IHs2iIY=",
"version": "100150.120.2"
},
"IONetworkingFamily": {
"hash": "sha256-gZ7Dkk4Iu7AV9K2ioqSeJ1W7bTNxv77bmT18iv3ljLg=",
"version": "185"
},
"IOSerialFamily": {
"hash": "sha256-wVS4QTx6MBOS0VrwyCZ3s5Usezwaf8rWzmNnfdDTXTU=",
"version": "93"
},
"IOStorageFamily": {
"hash": "sha256-/0H0tqWUWkgYigYypucbc7lOCFYDuukwF9fvLEOhwOk=",
"version": "323"
},
"IOUSBFamily": {
"hash": "sha256-Z0E3TfKP49toYo1Fo9kElRap8CZ+mVDHy5RIexgJTpA=",
"version": "630.4.5"
},
"Libc": {
"hash": "sha256-nWDokN0Vr5pUyNGculnDOah9RNgHiWr3S13RSQLmZrc=",
"version": "1698.100.8"
},
"Libinfo": {
"hash": "sha256-UI5mGvzZ6BPafGYD6CrNAJAKjeJLB6urAS2lpB6X/Ec=",
"version": "597"
},
"Libm": {
"hash": "sha256-p4BndAag9d0XSMYWQ+c4myGv5qXbKx5E1VghudSbpTk=",
"version": "2026"
},
"Libnotify": {
"hash": "sha256-GDYMVi1034f9empq0YOuumQp/BDJ7phTb0Zl4KTY9xg=",
"version": "342"
},
"Librpcsvc": {
"hash": "sha256-UWYdCQ9QsBqwM01bWr+igINAHSdSluB/FrOclC5AjTI=",
"version": "31"
},
"Libsystem": {
"hash": "sha256-nawWJiu2IJ34ek5iOX6CrlqMzev7TuJpUkvDp30ZQ/U=",
"version": "1351"
},
"OpenDirectory": {
"hash": "sha256-6fSl8PasCZSBfe0ftaePcBuSEO3syb6kK+mfDI6iR7A=",
"version": "146"
},
"Security": {
"hash": "sha256-ZOrOOCk+hZbzDilzkihpQfsDpzV3Ul4zy6fpFRWUQHw=",
"version": "61439.120.27"
},
"architecture": {
"hash": "sha256-PRNUrhzSOrwmxSPkKmV0LV7yEIik65sdkfKdBqcwFhU=",
"version": "282"
},
"configd": {
"hash": "sha256-ZdUq1SrOwB88Lx68ekrA4zeVsLDZz4TAJywNnF+uAzY=",
"version": "1351.120.3"
},
"copyfile": {
"hash": "sha256-rLqT6e44W2ohgwUXREmiOyJBYCrV3gRLbtVnbUq60xc=",
"version": "221.121.1"
},
"dtrace": {
"hash": "sha256-iNEZyxK3DmEwO3gzrfvCaVZSEuuOMQm5IG/6FodPNdI=",
"version": "411"
},
"dyld": {
"hash": "sha256-4OOghgUYyMJbsTe96fiWCndTJ1BS94rK9v6Kqn/ooYs=",
"version": "1285.19"
},
"eap8021x": {
"hash": "sha256-Kx/wwnt108hDm0qQPyTNbZ8KoHkD5m7L4yb5qjSuQjI=",
"version": "365.120.2"
},
"hfs": {
"hash": "sha256-5/3Ycp3cKqlgAl1kjBmbF5tFlfJYQS5rbrbk4SS66b8=",
"version": "683.120.3"
},
"launchd": {
"hash": "sha256-8mW9bnuHmRXCx9py8Wy28C5b2QPICW0rlAps5njYa00=",
"version": "842.1.4"
},
"libclosure": {
"hash": "sha256-pvwfcbeEJmTEPdt6/lgVswiabLRG+sMN6VT5FwG7C4Q=",
"version": "96"
},
"libdispatch": {
"hash": "sha256-jTp2DolOOCQPBt1HRotkmPnKgQ2LGgniEqeHoM+vlKg=",
"version": "1521.120.4"
},
"libmalloc": {
"hash": "sha256-d9AVHSYTqHDlgctv8Hh4HAYW53MJelj4F8LWPsjrsws=",
"version": "715.120.13"
},
"libplatform": {
"hash": "sha256-gpijoTMvdkM0PdG8gyIllOJlh/MtTc4ro9ODDAhN6gM=",
"version": "349"
},
"libpthread": {
"hash": "sha256-N+MMXdbthsxauTTfZ5ElUs39dVH+Chn1yyU6pObZpkU=",
"version": "536"
},
"mDNSResponder": {
"hash": "sha256-ILx12PRxj/+VqfpCCErJFEJXFI9yzTh4g+FK0UCenIE=",
"version": "2600.120.12"
},
"objc4": {
"hash": "sha256-DMxa25gXjKCkiDnVJ/8SyJUjaBlmBGABg8EfCHcmTj0=",
"version": "940.4"
},
"ppp": {
"hash": "sha256-8+QUA79sHf85yvGSPE9qCmGsrZDT3NZnbgZVroJw/Hg=",
"version": "1016"
},
"removefile": {
"hash": "sha256-Z5UD0mk/s80CQB0PZWDzSl2JWXmnVmwUvlNb28+hR3k=",
"version": "81"
},
"xnu": {
"hash": "sha256-o4tCuCAIgAYg/Li3wTs12mVWr5C/4vbwu1zi+kJ9d6w=",
"version": "11417.121.6"
}
},
"26.0": {
"CarbonHeaders": {
"hash": "sha256-nIPXnLr21yVnpBhx9K5q3l/nPARA6JL/dED08MeyhP8=",
"version": "18.1"
},
"CommonCrypto": {
"hash": "sha256-+qAwL6+s7di9cX/qXtapLkjCFoDuZaSYltRJEG4qekM=",
"version": "600035"
},
"IOAudioFamily": {
"hash": "sha256-A3iiAjjP29VdjMj40tLS5Q/ni4qeh9bBpnmNzeG2pIY=",
"version": "700.2"
},
"IOBDStorageFamily": {
"hash": "sha256-OcQUJ3nEfrpvWX/npnedJ4PECIGWFSLiM0PKoiH911w=",
"version": "26"
},
"IOCDStorageFamily": {
"hash": "sha256-p/2qM5zjXFDRb/DISpEHxQEdvmuLlRGt/Ygc71Yu2rI=",
"version": "62"
},
"IODVDStorageFamily": {
"hash": "sha256-1Sa8aZBGNtqJBNHva+YXxET6Wcdm2PgVrTzYT/8qrN4=",
"version": "46"
},
"IOFWDVComponents": {
"hash": "sha256-WkfkWnzRupEh20U7vjsTta89clhus6GTkOpXQWXw/bM=",
"version": "208"
},
"IOFireWireAVC": {
"hash": "sha256-qR9lSTa7PN5Z9Nis4tfuXlcZGMIU48dete/NPD0UBbE=",
"version": "436"
},
"IOFireWireFamily": {
"hash": "sha256-hmErAXjLWIelqJaCrB8J4IiIxyB7S6EHFY+AY9YhmKQ=",
"version": "492"
},
"IOFireWireSBP2": {
"hash": "sha256-Xk+PDnUaO9q46nQwHwTKf/QXtGclfs0wTWiUbcV7e4s=",
"version": "454"
},
"IOFireWireSerialBusProtocolTransport": {
"hash": "sha256-cM/VFhVWNVwdJYk+mme0UYttQd7eJwd7Hlo7KNRyHY0=",
"version": "262"
},
"IOGraphics": {
"hash": "sha256-iysZE42mOKZbFxSZBNspaBTCRKEKK38DFGBxZWQxZxI=",
"version": "599"
},
"IOHIDFamily": {
"hash": "sha256-YLnabX90g4Q8LxjwVuJF6KODCDxychWV+VJaNG9d8fI=",
"version": "2222.0.24"
},
"IOKitUser": {
"hash": "sha256-ngwi8YMUqE0q8j7Lr5cqJwi2V+IDu3ie3bduotHIUJU=",
"version": "100222.0.4"
},
"IONetworkingFamily": {
"hash": "sha256-ZF5ML41Y1l1liQn32qTkcl4mMvx9Xdizb9VgvTzVTL4=",
"version": "186"
},
"IOSerialFamily": {
"hash": "sha256-wVS4QTx6MBOS0VrwyCZ3s5Usezwaf8rWzmNnfdDTXTU=",
"version": "93"
},
"IOStorageFamily": {
"hash": "sha256-1FKSF622qeXPGngA3UmQ2M/IU1pdlMoYBPbXytUFDaQ=",
"version": "331"
},
"IOUSBFamily": {
"hash": "sha256-Z0E3TfKP49toYo1Fo9kElRap8CZ+mVDHy5RIexgJTpA=",
"version": "630.4.5"
},
"Libc": {
"hash": "sha256-k+HQ+qgye0ORFm0hU8WzE4ysbbEoFZ7wcbVl5giDH/E=",
"version": "1725.0.11"
},
"Libinfo": {
"hash": "sha256-4InBEPi0n2EMo/8mIBib1Im4iTKRcRJ4IlAcLCigVGk=",
"version": "600"
},
"Libm": {
"hash": "sha256-p4BndAag9d0XSMYWQ+c4myGv5qXbKx5E1VghudSbpTk=",
"version": "2026"
},
"Libnotify": {
"hash": "sha256-p8cJZlBYOFmI1NDHXGYjgcv8z9Ldc1amZuYlxxJfeVY=",
"version": "344.0.1"
},
"Librpcsvc": {
"hash": "sha256-UWYdCQ9QsBqwM01bWr+igINAHSdSluB/FrOclC5AjTI=",
"version": "31"
},
"Libsystem": {
"hash": "sha256-/NlSwPaoTVx+bl9hYsfz3C5MuLdqGv4vdAh0KDbDKmY=",
"version": "1356"
},
"OpenDirectory": {
"hash": "sha256-6fSl8PasCZSBfe0ftaePcBuSEO3syb6kK+mfDI6iR7A=",
"version": "146"
},
"Security": {
"hash": "sha256-oxOvZsDoNYZNiWf+MASHrR4Q2o5oaqvK2We51hH7CO8=",
"version": "61901.0.87.0.1"
},
"architecture": {
"hash": "sha256-PRNUrhzSOrwmxSPkKmV0LV7yEIik65sdkfKdBqcwFhU=",
"version": "282"
},
"configd": {
"hash": "sha256-58or+OQP788UgQKO7Y8k8pY/enaSqH971ks7xCPu8fA=",
"version": "1385.0.7"
},
"copyfile": {
"hash": "sha256-I9uDi5BDQKa7mO3XpHxv0d6PiROW2ueZ3vGfrsG0OJo=",
"version": "230.0.1.0.1"
},
"dtrace": {
"hash": "sha256-5HpH6Cg8vWWzOX5ADD//izKDvqGnzV05Giju8lmGeyA=",
"version": "413"
},
"dyld": {
"hash": "sha256-jzoFLwbms0rUwzyjYif/r6Rmr4kyn+as/bhc4paEPeY=",
"version": "1323.3"
},
"eap8021x": {
"hash": "sha256-17bseWT4OWMA8hF+YSDDjxhVyJpbpP2xwv8dGti1YoM=",
"version": "368.0.3"
},
"hfs": {
"hash": "sha256-OkgqZ03gwn2hTuHxZrPDmQOrY4Dwu7MrX+BfG+PTgvE=",
"version": "704.0.3.0.2"
},
"launchd": {
"hash": "sha256-8mW9bnuHmRXCx9py8Wy28C5b2QPICW0rlAps5njYa00=",
"version": "842.1.4"
},
"libclosure": {
"hash": "sha256-pvwfcbeEJmTEPdt6/lgVswiabLRG+sMN6VT5FwG7C4Q=",
"version": "96"
},
"libdispatch": {
"hash": "sha256-L0+Ho9dAlMXVpqFEGIcIMsJc0gULckRulUImNEZe5MU=",
"version": "1542.0.4"
},
"libmalloc": {
"hash": "sha256-482hgm1ESr3LWC/JhuQNGNu9smsa2Eap49/eH+YNAio=",
"version": "792.1.1"
},
"libplatform": {
"hash": "sha256-wGZ2Im81mRXx6epgj/tbOJpg89CEbAr0Z8oFEpkyNMU=",
"version": "359.1.2"
},
"libpthread": {
"hash": "sha256-VuMpQjxuMsdHsFq0q6QIWSWi88gVF2jNzIfti20Gkbw=",
"version": "539"
},
"mDNSResponder": {
"hash": "sha256-iRqCpPAQDRjgRbRz3s6q2oyzq6xo+w4FTBai79104Zo=",
"version": "2881.0.25"
},
"objc4": {
"hash": "sha256-Nlgr36yLvGkUJIEFQ5w8FAB0r2syEsRTw0KuUShNT8E=",
"version": "950"
},
"ppp": {
"hash": "sha256-FzHZ05o7JxwgTqz0e3D68b/DiLu2x2ErzGMh0U78fLo=",
"version": "1020.1.1"
},
"removefile": {
"hash": "sha256-Z5UD0mk/s80CQB0PZWDzSl2JWXmnVmwUvlNb28+hR3k=",
"version": "84"
},
"xnu": {
"hash": "sha256-Cuf7kPtsn4CPXqyZmxVsJlA5i+Ikryp8ezJyGrvT63c=",
"version": "12377.1.9"
}
}
}
@@ -0,0 +1,533 @@
[
{
"package": "apache",
"headers": [
"apache2"
]
},
{
"package": "apr",
"headers": [
"apr-1"
],
"libraries": [
"libapr-1.*",
"libaprutil-1.*"
]
},
{
"package": "boringssl",
"libraries": [
"libboringssl.*"
]
},
{
"package": "bzip2",
"headers": [
"bzlib.h"
],
"libraries": [
"libbz2.*"
]
},
{
"package": "corecrypto",
"libraries": [
"system/libcorecrypto*"
]
},
{
"package": "Csu",
"libraries": [
"*.o"
]
},
{
"package": "cups",
"headers": [
"cups"
],
"libraries": [
"libcups*"
]
},
{
"package": "curl",
"headers": [
"curl"
],
"libraries": [
"libcurl.*"
]
},
{
"package": "cyrus_sasl",
"headers": [
"sasl"
],
"libraries": [
"libsasl*"
]
},
{
"package": "editline",
"headers": [
"editline.h",
"editline"
],
"libraries": [
"libedit.*",
"libeditline.*"
]
},
{
"package": "html-tidy",
"headers": [
"tidy*"
],
"libraries": [
"libtidy.*"
]
},
{
"package": "hunspell",
"headers": [
"hunspell"
],
"libraries": [
"libhunspell*"
]
},
{
"package": "icu",
"headers": [
"unicode"
],
"libraries": [
"libicucore.*"
]
},
{
"package": "libarchive",
"headers": [
"archive.h",
"archive_entry.h"
],
"libraries": [
"libarchive.*"
]
},
{
"package": "libc++",
"headers": [
"c++",
"cxxabi.h",
"__cxxabi_config.h"
],
"libraries": [
"libc++*"
]
},
{
"package": "ld64",
"libraries": [
"libcodedirectory.*",
"libcodedirectory_static.*"
]
},
{
"package": "expat",
"headers": [
"expat.h",
"expat_config.h",
"expat_external.h"
],
"libraries": [
"libexpat.*"
]
},
{
"package": "libffi",
"headers": [
"ffi*"
],
"libraries": [
"libffi*"
]
},
{
"package": "libgcc",
"libraries": [
"libgcc*"
]
},
{
"package": "libiconv",
"headers": [
"iconv.h",
"libcharset.h",
"localcharset.h"
],
"libraries": [
"libcharset.*",
"libiconv.*",
"i18n"
]
},
{
"package": "libiodbc",
"libraries": [
"libiodbc*"
]
},
{
"package": "libkrb4",
"libraries": [
"libkrb4.*"
]
},
{
"package": "libkrb5",
"headers": [
"com_err.h",
"gssapi",
"gssapi.h",
"gssrpc",
"kadm5",
"kdb.h",
"krad.h",
"krb5",
"krb5.h",
"profile.h",
"verto-module.h",
"verto.h"
],
"libraries": [
"krb5",
"libcom_err.*",
"libgssapi_krb5.*",
"libgssrpc.*",
"libk5crypto.*",
"libkadm5clnt.*",
"libkadm5clnt_mit.*",
"libkadm5srv.*",
"libkadm5srv_mit.*",
"libkdb5.*",
"libkrad.*",
"libkrb5*",
"libkrb5support.*",
"libverto.*"
]
},
{
"package": "libpcap",
"headers": [
"pcap*"
],
"libraries": [
"libpcap.*"
]
},
{
"package": "libresolv",
"headers": [
"arpa/nameser.h",
"arpa/nameser_compat.h",
"dns.h",
"dns_util.h",
"nameser.h",
"resolv.h"
],
"libraries": [
"libresolv.*"
]
},
{
"package": "libstdc++",
"libraries": [
"libstdc++.*"
]
},
{
"package": "libsbuf",
"headers": [
"usbuf.h"
],
"libraries": [
"libsbuf.*"
]
},
{
"package": "libtermcap",
"headers": [
"termcap.h"
],
"libraries": [
"libtermcap.*"
]
},
{
"package": "libutil",
"headers": [
"libutil.h"
],
"libraries": [
"libutil.*",
"libutil1.*"
]
},
{
"package": "libxml2",
"headers": [
"libxml",
"libxml2"
],
"libraries": [
"libxml2.*"
]
},
{
"package": "libxo",
"headers": [
"libxo"
],
"libraries": [
"libxo.*"
]
},
{
"package": "libxslt",
"headers": [
"libexslt",
"libxslt"
],
"libraries": [
"libexslt.*",
"libxslt.*"
]
},
{
"package": "liby",
"libraries": [
"liby.a"
]
},
{
"package": "marisa-trie",
"libraries": [
"libmarisa.*"
]
},
{
"package": "ncurses",
"headers": [
"curses*",
"cursslk.h",
"eti.h",
"etip.h",
"form.h",
"menu.h",
"nc_tparm.h",
"ncurses*",
"panel.h",
"term.h",
"term_entry.h",
"termcap.h",
"tic.h",
"unctrl.h"
],
"libraries": [
"libcurses.*",
"libform.*",
"libformw.*",
"libmenu.*",
"libmenuw.*",
"libncurses.*",
"libncursesw.*",
"libpanel.*",
"libpanelw.*",
"libtinfo.*"
]
},
{
"package": "net-snmp",
"headers": [
"net-snmp"
],
"libraries": [
"libnetsnmp*"
]
},
{
"package": "nghttp",
"libraries": [
"lib*nghttp2.*"
]
},
{
"package": "openblas",
"headers": [
"cblas.h",
"f77blas.h",
"lapack.h",
"lapacke.h",
"lapacke_config.h",
"lapacke_mangling.h",
"lapacke_utils.h",
"openblas_config.h"
],
"libraries": [
"libblas.*",
"libcblas.*",
"libclapack.*",
"libf77lapack.*",
"liblapack.*",
"liblapacke.*",
"libopenblas.*",
"libopenblas.*",
"libopenblasp*"
]
},
{
"package": "openldap",
"libraries": [
"liblber.*",
"liblber_r.*",
"libldap.*",
"libldap_r.*"
]
},
{
"package": "openpam",
"headers": [
"security"
],
"libraries": [
"libpam.*",
"pam_*"
]
},
{
"package": "pcre",
"headers": [
"pcre.h",
"pcreposix.h"
],
"libraries": [
"libpcre.*",
"libpcre2*",
"libpcreposix.*"
]
},
{
"package": "php",
"headers": [
"php"
],
"libraries": [
"php"
]
},
{
"package": "postgresql",
"libraries": [
"libecpg*",
"libpg*",
"libpq*"
]
},
{
"package": "python",
"headers": [
"python*"
],
"frameworks": [
"Python.framework"
],
"libraries": [
"libpython*",
"python*"
]
},
{
"package": "readline",
"headers": [
"readline"
],
"libraries": [
"libhistory.*",
"libreadline.*"
]
},
{
"package": "ruby",
"frameworks": [
"Ruby.framework"
],
"libraries": [
"libruby.*",
"ruby"
]
},
{
"package": "sqlite3",
"headers": [
"sqlite3.h",
"sqlite3ext.h"
],
"libraries": [
"libsqlite3.*"
]
},
{
"package": "swift",
"libraries": [
"swift/shims"
]
},
{
"package": "tcl",
"headers": [
"tcl*",
"tk*"
],
"frameworks": [
"Tcl.framework",
"Tk.framework"
],
"libraries": [
"libtcl*",
"libtk*",
"tclConfig.sh",
"tkConfig.sh"
]
},
{
"package": "xar",
"headers": [
"xar"
],
"libraries": [
"libxar.*"
]
},
{
"package": "xz",
"headers": [
"lzma*"
],
"libraries": [
"liblzma.*"
]
},
{
"package": "zlib",
"headers": [
"zconf.h",
"zlib.h"
],
"libraries": [
"libz.*"
]
}
]
+110
View File
@@ -0,0 +1,110 @@
let
sdkVersions = builtins.fromJSON (builtins.readFile ./metadata/versions.json);
in
{ lib
, stdenv
, stdenvNoCC
, substitute
, # Specifies the major version used for the SDK. Uses `hostPlatform.darwinSdkVersion` by default.
darwinSdkMajorVersion ? lib.versions.major stdenv.hostPlatform.darwinSdkVersion
, # Enabling bootstrap disables propagation. Defaults to `false` (meaning to propagate certain packages and `xcrun`)
# except in stage0 of the Darwin stdenv bootstrap.
enableBootstrap ? stdenv.name == "bootstrap-stage0-stdenv-darwin"
, # Required by various phases
callPackage
,
}:
let
sdkInfo =
sdkVersions.${darwinSdkMajorVersion}
or (lib.throw "Unsupported SDK major version: ${darwinSdkMajorVersion}");
sdkVersion = sdkInfo.version;
fetchSDK = callPackage ./common/fetch-sdk.nix { };
phases = lib.composeManyExtensions (
[
(callPackage ./common/add-core-symbolication.nix { })
(callPackage ./common/derivation-options.nix { })
(callPackage ./common/passthru-private-frameworks.nix { inherit sdkVersion; })
(callPackage ./common/passthru-source-release-files.nix { inherit sdkVersion; })
(callPackage ./common/remove-disallowed-packages.nix { })
(callPackage ./common/process-stubs.nix { })
]
# Avoid infinite recursions by not propagating certain packages, so they can themselves build with the SDK.
++ lib.optionals (!enableBootstrap) [
(callPackage ./common/propagate-inputs.nix { })
(callPackage ./common/propagate-xcrun.nix { inherit sdkVersion; })
]
# This has to happen last.
++ [
(callPackage ./common/run-build-phase-hooks.nix { })
]
);
in
stdenvNoCC.mkDerivation (
lib.extends phases (finalAttrs: {
pname = "apple-sdk";
inherit (sdkInfo) version;
src = fetchSDK sdkInfo;
dontConfigure = true;
strictDeps = true;
setupHooks = [
# `role.bash` is copied from `../build-support/setup-hooks/role.bash` due to the requirements not to reference
# paths outside the package when it is in `by-name`. It needs to be kept in sync, but it fortunately does not
# change often. Once `build-support` is available as a package (or some other mechanism), it should be changed
# to whatever that replacement is.
./setup-hooks/role.bash
(substitute {
src = ./setup-hooks/sdk-hook.sh;
substitutions = [
"--subst-var-by"
"sdkVersion"
(lib.escapeShellArgs (lib.splitVersion sdkVersion))
];
})
];
installPhase =
let
sdkName = "MacOSX${lib.versions.majorMinor sdkVersion}.sdk";
sdkMajor = lib.versions.major sdkVersion;
in
''
runHook preInstall
mkdir -p "$sdkpath"
cp -rd . "$sdkpath/${sdkName}"
ln -s "${sdkName}" "$sdkpath/MacOSX${sdkMajor}.sdk"
ln -s "${sdkName}" "$sdkpath/MacOSX.sdk"
# Swift adds these locations to its search paths. Avoid spurious warnings by making sure they exist.
mkdir -p "$platformPath/Developer/Library/Frameworks"
mkdir -p "$platformPath/Developer/Library/PrivateFrameworks"
mkdir -p "$platformPath/Developer/usr/lib"
runHook postInstall
'';
passthru = {
sdkroot = finalAttrs.finalPackage + "/Platforms/MacOSX.platform/Developer/SDKs/MacOSX.sdk";
};
__structuredAttrs = true;
meta = {
description = "Frameworks and libraries required for building packages on Darwin";
homepage = "https://developer.apple.com";
teams = [ lib.teams.darwin ];
platforms = lib.platforms.darwin;
badPlatforms = [ lib.systems.inspect.patterns.is32bit ];
};
})
)
@@ -0,0 +1,48 @@
From 6531da946949a94643e6d8424236174ae64fe0ca Mon Sep 17 00:00:00 2001
From: Randy Eckenrode <randy@largeandhighquality.com>
Date: Sat, 30 Sep 2023 18:02:39 -0400
Subject: [PATCH 1/2] Add function definitions needed to build zlog in
system_cmds
---
CoreSymbolication.h | 10 +++++++---
1 file changed, 7 insertions(+), 3 deletions(-)
diff --git a/CoreSymbolication.h b/CoreSymbolication.h
index a413860..f3cf63f 100644
--- a/CoreSymbolication.h
+++ b/CoreSymbolication.h
@@ -324,7 +324,9 @@ CSSymbolOwnerEditRelocations
CSSymbolOwnerForeachRegion
CSSymbolOwnerForeachRegionWithName
CSSymbolOwnerForeachSection
-CSSymbolOwnerForeachSegment
+*/
+void CSSymbolOwnerForeachSegment(CSSymbolOwnerRef owner, void (^block)(CSSegmentRef));
+/*
CSSymbolOwnerForeachSourceInfo
CSSymbolOwnerForeachSymbol
*/
@@ -333,7 +335,9 @@ void CSSymbolOwnerForeachSymbolWithName(CSSymbolOwnerRef owner, const char *sna
/*
CSSymbolOwnerGetArchitecture
CSSymbolOwnerGetBaseAddress
-CSSymbolOwnerGetCFUUIDBytes
+*/
+const CFUUIDBytes* CSSymbolOwnerGetCFUUIDBytes(CSSymbolOwnerRef owner);
+/*
CSSymbolOwnerGetCompatibilityVersion
CSSymbolOwnerGetCurrentVersion
CSSymbolOwnerGetDataFlags
@@ -390,7 +394,7 @@ CSSymbolOwnerSetLoadTimestamp
CSSymbolOwnerSetPath
CSSymbolOwnerSetRelocationCount
*/
-CSSymbolOwnerSetTransientUserData(CSSymbolOwnerRef owner, uint32_t gen);
+void CSSymbolOwnerSetTransientUserData(CSSymbolOwnerRef owner, uint32_t gen);
/*
CSSymbolOwnerSetUnloadTimestamp
*/
--
2.44.1
@@ -0,0 +1,45 @@
From ae7ac6a7043dbae8e63d6ce5e63dfaf02b5977fe Mon Sep 17 00:00:00 2001
From: Randy Eckenrode <randy@largeandhighquality.com>
Date: Sat, 30 Sep 2023 18:37:18 -0400
Subject: [PATCH 2/2] Add CF_EXPORT To const symbols
---
CoreSymbolication.h | 15 ++++++++-------
1 file changed, 8 insertions(+), 7 deletions(-)
diff --git a/CoreSymbolication.h b/CoreSymbolication.h
index f3cf63f..4124a54 100644
--- a/CoreSymbolication.h
+++ b/CoreSymbolication.h
@@ -49,6 +49,7 @@
#include <CoreFoundation/CoreFoundation.h>
+#include <CoreFoundation/CFBase.h>
#include <mach/mach.h>
@@ -139,13 +140,13 @@ typedef void (^CSSegmentIterator)(CSSegmentRef segment);
* External symbols
*/
-const char* kCSRegionMachHeaderName;
-const CSDictionaryKeyCallBacks kCSTypeDictionaryKeyCallBacks;
-const CSDictionaryValueCallBacks kCSTypeDictionaryValueCallBacks;
-const CSDictionaryKeyCallBacks kCSTypeDictionaryWeakKeyCallBacks;
-const CSDictionaryValueCallBacks kCSTypeDictionaryWeakValueCallBacks;
-const CSSetCallBacks kCSTypeSetCallBacks;
-const CSSetCallBacks kCSTypeSetWeakCallBacks;
+CF_EXPORT const char* kCSRegionMachHeaderName;
+CF_EXPORT const CSDictionaryKeyCallBacks kCSTypeDictionaryKeyCallBacks;
+CF_EXPORT const CSDictionaryValueCallBacks kCSTypeDictionaryValueCallBacks;
+CF_EXPORT const CSDictionaryKeyCallBacks kCSTypeDictionaryWeakKeyCallBacks;
+CF_EXPORT const CSDictionaryValueCallBacks kCSTypeDictionaryWeakValueCallBacks;
+CF_EXPORT const CSSetCallBacks kCSTypeSetCallBacks;
+CF_EXPORT const CSSetCallBacks kCSTypeSetWeakCallBacks;
/*
--
2.44.1
@@ -0,0 +1,41 @@
#!/usr/bin/env nix-shell
#!nix-shell -i bash -p coreutils curl file gzip jq xcbuild yq
set -eu -o pipefail
catalog=${1-}
if [ -z "$catalog" ]; then
echo "usage: get-sdks-from-catalog.sh <catalog>"
echo " <catalog> Apple software update catalog (may be gzipped)" >&2
exit 1
fi
scratch=$(mktemp)
trap 'rm -f -- "$scratch"' EXIT
if [[ "$(file "$catalog")" =~ gzip ]]; then
gzcat "$catalog" >"$scratch"
else
cp --reflink=auto "$catalog" "$scratch"
fi
# Grab all SDK packages from the catalog
filter='.Products[].Packages[] | select(.URL | test(".*CLTools_macOSNMOS_SDK.pkg")) | "\(.URL)|\(.MetadataURL)"'
declare -A package_list
for package in $(plutil -convert json -o - "$scratch" | jq -r "$filter"); do
package_list[${package%%|*}]=${package#*|}
done
truncate --size 0 "$scratch"
for pkg in "${!package_list[@]}"; do
ver=$(curl --silent "${package_list[$pkg]}" | xq -r '."pkg-info"."@version"')
echo "{\"url\": \"$pkg\", \"version\": \"$(cut -d. -f1-3 <<<"$ver")\", \"long_version\": \"$ver\"}" >>"$scratch"
done
jq -r --slurp '
group_by(.version | split(".")[0])
| map(max_by(.version))
| sort_by(.version)[]
| "Package URL: \(.url)\n Xcode Ver: \(.version) (\(.long_version))\n"' "$scratch"
+70
View File
@@ -0,0 +1,70 @@
#!/usr/bin/env nix-shell
#!nix-shell -i bash -p coreutils curl git gnutar jq moreutils nix
set -eu -o pipefail
if [ ! -v 2 ]; then
echo "usage: lock-sdk-deps.sh <SDK version> <Packages>" >&2
echo " <SDK version> Decimal-separated version number." >&2
echo " Must correspond to a tag in https://github.com/apple-oss-distributions/distribution-macOS" >&2
echo " <Packages> List of packages from the distributions-macOS repository." >&2
echo " Packages not in the repository at the tag for <SDK version> will be ignored."
exit 1
fi
pkgdir=$(dirname "$(dirname "$(realpath "$0")")")
lockfile=$pkgdir/metadata/apple-oss-lockfile.json
if [ ! -e "$lockfile" ]; then
touch "$lockfile"
fi
workdir=$(mktemp -d)
trap 'rm -rf -- "$workdir"' EXIT
sdkVersion=$1
shift
tag="macos-${sdkVersion//./}"
declare -a packages=("$@")
echo "Locking versions for macOS $sdkVersion using tag '$tag'..."
pushd "$workdir" >/dev/null
git clone --branch "$tag" https://github.com/apple-oss-distributions/distribution-macOS.git &>/dev/null
cd distribution-macOS
for package in "${packages[@]}"; do
# If the tag exists in `release.json`, use that as an optimization to avoid downloading unnecessarily from Github.
packageTag=$(jq -r --arg package "$package" '.projects[] | select(.project == $package) | .tag' release.json)
packageCommit=$(git ls-tree -d HEAD "$package" | awk '{print $3}')
if [ ! -d "$package" ]; then
packageCommit=HEAD
fi
# However, sometimes it doesnt exist. In that case, fall back to cloning the repo and check manually
# which tag corresponds to the commit from the submodule.
if [ -z "$packageTag" ]; then
git clone --no-checkout "https://github.com/apple-oss-distributions/$package.git" ../source &>/dev/null
pushd ../source >/dev/null
packageTag=$(git tag --points-at "$packageCommit")
popd >/dev/null
rm -rf ../source
fi
packageVersion=${packageTag##"$package"-}
curl -OL "https://github.com/apple-oss-distributions/$package/archive/$packageTag.tar.gz" &>/dev/null
tar axf "$packageTag.tar.gz"
packageHash=$(nix --extra-experimental-features nix-command hash path "$package-$packageTag")
pkgsjson="{\"$sdkVersion\": {\"$package\": {\"version\": \"$packageVersion\", \"hash\": \"$packageHash\"}}}"
echo " - Locking $package to version $packageVersion with hash '$packageHash'"
jq --argjson pkg "$pkgsjson" -S '. * $pkg' "$lockfile" | sponge "$lockfile"
done
popd >/dev/null
@@ -0,0 +1,62 @@
#!/usr/bin/env nix-shell
#!nix-shell -i bash -p coreutils jq
set -eu -o pipefail
pkgdir=$(dirname "$(dirname "$(realpath "$0")")")
echo '{}' >"$pkgdir/metadata/apple-oss-lockfile.json"
declare -a versions
readarray -t versions < <(jq -r '.[].version' "$pkgdir/metadata/versions.json")
declare -a packages=(
CarbonHeaders
CommonCrypto
IOAudioFamily
IOFireWireFamily
IOFWDVComponents
IOFireWireAVC
IOFireWireSBP2
IOFireWireSerialBusProtocolTransport
IOGraphics
IOHIDFamily
IONetworkingFamily
IOSerialFamily
IOStorageFamily
IOBDStorageFamily
IOCDStorageFamily
IODVDStorageFamily
IOUSBFamily
IOKitUser
Libc
Libinfo
Libm
Libnotify
Librpcsvc
Libsystem
OpenDirectory
Security
architecture
configd
copyfile
dtrace
dyld
eap8021x
hfs
launchd
libclosure
libdispatch
libmalloc
libplatform
libpthread
mDNSResponder
objc4
ppp
removefile
xnu
)
for version in "${versions[@]}"; do
"$pkgdir/scripts/lock-sdk-deps.sh" "$version" "${packages[@]}"
done
@@ -0,0 +1,6 @@
function enablePrivateFrameworks() {
export NIX_CFLAGS_COMPILE+=" -iframework $DEVELOPER_DIR/Platforms/MacOSX.platform/Developer/SDKs/MacOSX.sdk/System/Library/PrivateFrameworks"
export NIX_LDFLAGS+=" -F$DEVELOPER_DIR/Platforms/MacOSX.platform/Developer/SDKs/MacOSX.sdk/System/Library/PrivateFrameworks"
}
preConfigureHooks+=(enablePrivateFrameworks)
+71
View File
@@ -0,0 +1,71 @@
# Since the same derivation can be depended on in multiple ways, we need to
# accumulate *each* role (i.e. host and target platforms relative the depending
# derivation) in which the derivation is used.
#
# The role is intended to be used as part of other variables names like
# - $NIX_SOMETHING${role_post}
function getRole() {
case $1 in
-1)
role_post='_FOR_BUILD'
;;
0)
role_post=''
;;
1)
role_post='_FOR_TARGET'
;;
*)
echo "@name@: used as improper sort of dependency" >&2
return 1
;;
esac
}
# `hostOffset` describes how the host platform of the package is slid relative
# to the depending package. `targetOffset` likewise describes the target
# platform of the package. Both are brought into scope of the setup hook defined
# for dependency whose setup hook is being processed relative to the package
# being built.
function getHostRole() {
getRole "$hostOffset"
}
function getTargetRole() {
getRole "$targetOffset"
}
# `depHostOffset` describes how the host platform of the dependencies are slid
# relative to the depending package. `depTargetOffset` likewise describes the
# target platform of dependenices. Both are brought into scope of the
# environment hook defined for the dependency being applied relative to the
# package being built.
function getHostRoleEnvHook() {
getRole "$depHostOffset"
}
function getTargetRoleEnvHook() {
getRole "$depTargetOffset"
}
# This variant is intended specifically for code-producing tool wrapper scripts
# `NIX_@wrapperName@_TARGET_*_@suffixSalt@` tracks this (needs to be an exported
# env var so can't use fancier data structures).
function getTargetRoleWrapper() {
case $targetOffset in
-1)
export NIX_@wrapperName@_TARGET_BUILD_@suffixSalt@=1
;;
0)
export NIX_@wrapperName@_TARGET_HOST_@suffixSalt@=1
;;
1)
export NIX_@wrapperName@_TARGET_TARGET_@suffixSalt@=1
;;
*)
echo "@name@: used as improper sort of dependency" >&2
return 1
;;
esac
}
+17
View File
@@ -0,0 +1,17 @@
local role_post
getHostRole
local sdkVersionVar=NIX_APPLE_SDK_VERSION${role_post}
local developerDirVar=DEVELOPER_DIR${role_post}
local sdkVersionArr=(@sdkVersion@)
local sdkVersion
sdkVersion=$(printf "%02d%02d%02d" "${sdkVersionArr[0]-0}" "${sdkVersionArr[1]-0}" "${sdkVersionArr[2]-0}")
if [ "$sdkVersion" -gt "${!sdkVersionVar-000000}" ]; then
export "$developerDirVar"='@out@'
export "$sdkVersionVar"="$sdkVersion"
export "SDKROOT${role_post}"="${!developerDirVar}/Platforms/MacOSX.platform/Developer/SDKs/MacOSX.sdk"
fi
unset -v role_post developerDirVar sdkVersion sdkVersionArr sdkVersionVar
+6 -6
View File
@@ -41,16 +41,16 @@ let
mlx = stdenv.mkDerivation rec {
pname = "mlx";
version = let v = "0.30.7.dev20260218+14841977"; in
version = let v = "0.30.5"; in
assert v == uvLockMlxVersion || throw "MLX version mismatch: nix/mlx.nix has ${v} but uv.lock has ${uvLockMlxVersion}. Update both the version and hash in nix/mlx.nix.";
v;
pyproject = true;
src = fetchFromGitHub {
owner = "rltakashige";
repo = "mlx-jaccl-fix-small-recv";
rev = "1484197707f35186ad3bd614357c7c47fdf86ebc";
hash = "sha256-FupCMoK/SF/ldfKuvMSAKECcOP8c+ANgkQlPZttDsLk=";
owner = "ml-explore";
repo = "mlx";
tag = "v${version}";
hash = "sha256-SV/3MXt+SuJ69XfLfXycold6KgtXSM7OE0KwMSNw+eE=";
};
patches = [
@@ -85,8 +85,8 @@ 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.cmakeBool "MLX_BUILD_CPU" true)
(lib.cmakeOptionType "filepath" "FETCHCONTENT_SOURCE_DIR_METAL_CPP" "${metal_cpp}")
(lib.cmakeOptionType "string" "CMAKE_OSX_DEPLOYMENT_TARGET" "${apple-sdk_26.version}")
(lib.cmakeOptionType "filepath" "CMAKE_OSX_SYSROOT" "${apple-sdk_26.passthru.sdkroot}")
+4 -7
View File
@@ -17,9 +17,9 @@ dependencies = [
"loguru>=0.7.3",
"exo_pyo3_bindings", # rust bindings
"anyio==4.11.0",
"mlx; sys_platform == 'darwin'",
"mlx[cpu]==0.30.6; sys_platform == 'linux'",
"mlx-lm==0.30.7",
"mlx==0.30.5; sys_platform == 'darwin'",
"mlx[cpu]==0.30.5; sys_platform == 'linux'",
"mlx-lm==0.30.6",
"tiktoken>=0.12.0", # required for kimi k2 tokenizer
"hypercorn>=0.18.0",
"openai-harmony>=0.0.8",
@@ -28,8 +28,6 @@ dependencies = [
"pillow>=11.0,<12.0", # compatibility with mflux
"mflux==0.15.5",
"python-multipart>=0.0.21",
"msgspec>=0.19.0",
"zstandard>=0.23.0",
]
[project.scripts]
@@ -64,7 +62,6 @@ members = [
[tool.uv.sources]
exo_pyo3_bindings = { workspace = true }
mlx = { git = "https://github.com/rltakashige/mlx-jaccl-fix-small-recv.git", branch = "address-rdma-gpu-locks", marker = "sys_platform == 'darwin'" }
#mlx-lm = { git = "https://github.com/davidmcc73/mlx-lm", branch = "stable" }
# Uncomment to use local mlx/mlx-lm development versions:
# mlx = { path = "/Users/Shared/mlx", editable=true }
@@ -133,7 +130,7 @@ markers = [
env = [
"EXO_TESTS=1"
]
addopts = "-m 'not slow' --ignore=tests/start_distributed_test.py"
addopts = "-m 'not slow'"
filterwarnings = [
"ignore:builtin type Swig:DeprecationWarning",
]
+7 -73
View File
@@ -14,9 +14,7 @@
# Override overlay to inject Nix-built components
exoOverlay = final: prev: {
# Replace workspace exo_pyo3_bindings with Nix-built wheel.
# Preserve passthru so mkVirtualEnv can resolve dependency groups.
# Copy .pyi stub + py.typed marker so basedpyright can find the types.
# Replace workspace exo_pyo3_bindings with Nix-built wheel
exo-pyo3-bindings = pkgs.stdenv.mkDerivation {
pname = "exo-pyo3-bindings";
version = "0.1.0";
@@ -24,12 +22,6 @@
# Install from pre-built wheel
nativeBuildInputs = [ final.pyprojectWheelHook ];
dontStrip = true;
passthru = prev.exo-pyo3-bindings.passthru or { };
postInstall = ''
local siteDir=$out/${final.python.sitePackages}/exo_pyo3_bindings
cp ${inputs.self}/rust/exo_pyo3_bindings/exo_pyo3_bindings.pyi $siteDir/
touch $siteDir/py.typed
'';
};
};
@@ -37,47 +29,17 @@
# 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;
mlx-cuda-13 = prev.mlx-cuda-13.overrideAttrs (old: {
buildInputs = (old.buildInputs or [ ]) ++ [
final.nvidia-cublas
final.nvidia-cuda-nvrtc
final.nvidia-cudnn-cu13
final.nvidia-nccl-cu13
];
preFixup = ''
addAutoPatchelfSearchPath ${final.nvidia-cublas}
addAutoPatchelfSearchPath ${final.nvidia-cuda-nvrtc}
addAutoPatchelfSearchPath ${final.nvidia-cudnn-cu13}
addAutoPatchelfSearchPath ${final.nvidia-nccl-cu13}
'';
autoPatchelfIgnoreMissingDeps = [ "libcuda.so.1" ];
});
torch = ignoreMissing prev.torch;
triton = ignoreMissing prev.triton;
}
);
pythonSet = (pkgs.callPackage inputs.pyproject-nix.build.packages {
inherit python;
}).overrideScope (
@@ -86,28 +48,16 @@
overlay
exoOverlay
buildSystemsOverlay
linuxOverlay
]
);
# mlx-cpu and mlx-cuda-13 both ship mlx/ site-packages files; keep first.
# mlx-cpu/mlx-cuda-13 and nvidia-cudnn-cu12/cu13 ship overlapping files.
venvCollisionPaths = lib.optionals pkgs.stdenv.hostPlatform.isLinux [
"lib/python3.13/site-packages/mlx*"
"lib/python3.13/site-packages/nvidia*"
];
exoVenv = (pythonSet.mkVirtualEnv "exo-env" workspace.deps.default).overrideAttrs {
venvIgnoreCollisions = venvCollisionPaths;
};
exoVenv = pythonSet.mkVirtualEnv "exo-env" workspace.deps.default;
# Virtual environment with dev dependencies for testing
testVenv = (pythonSet.mkVirtualEnv "exo-test-env" (
testVenv = pythonSet.mkVirtualEnv "exo-test-env" (
workspace.deps.default // {
exo = [ "dev" ]; # Include pytest, pytest-asyncio, pytest-env
}
)).overrideAttrs {
venvIgnoreCollisions = venvCollisionPaths;
};
);
mkPythonScript = name: path: pkgs.writeShellApplication {
inherit name;
@@ -158,7 +108,6 @@
exo-test-env = testVenv;
} // {
exo-bench = mkBenchScript "exo-bench" (inputs.self + /bench/exo_bench.py);
exo-eval-tool-calls = mkBenchScript "exo-eval-tool-calls" (inputs.self + /bench/eval_tool_calls.py);
exo-get-all-models-on-cluster = mkSimplePythonScript "exo-get-all-models-on-cluster" (inputs.self + /tests/get_all_models_on_cluster.py);
};
@@ -169,21 +118,6 @@
${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
'';
};
};
}
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
family = "deepseek"
quantization = "4bit"
base_model = "DeepSeek V3.1"
capabilities = ["text", "thinking", "thinking_toggle"]
capabilities = ["text", "thinking"]
[storage_size]
in_bytes = 405874409472
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
family = "deepseek"
quantization = "8bit"
base_model = "DeepSeek V3.1"
capabilities = ["text", "thinking", "thinking_toggle"]
capabilities = ["text", "thinking"]
[storage_size]
in_bytes = 765577920512
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
family = "glm"
quantization = "8bit"
base_model = "GLM 4.5 Air"
capabilities = ["text", "thinking", "thinking_toggle"]
capabilities = ["text", "thinking"]
[storage_size]
in_bytes = 122406567936
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
family = "glm"
quantization = "bf16"
base_model = "GLM 4.5 Air"
capabilities = ["text", "thinking", "thinking_toggle"]
capabilities = ["text", "thinking"]
[storage_size]
in_bytes = 229780750336
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
family = "glm"
quantization = "4bit"
base_model = "GLM 4.7"
capabilities = ["text", "thinking", "thinking_toggle"]
capabilities = ["text", "thinking"]
[storage_size]
in_bytes = 198556925568
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
family = "glm"
quantization = "6bit"
base_model = "GLM 4.7"
capabilities = ["text", "thinking", "thinking_toggle"]
capabilities = ["text", "thinking"]
[storage_size]
in_bytes = 286737579648
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
family = "glm"
quantization = "8bit"
base_model = "GLM 4.7"
capabilities = ["text", "thinking", "thinking_toggle"]
capabilities = ["text", "thinking"]
[storage_size]
in_bytes = 396963397248
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
family = "glm"
quantization = "4bit"
base_model = "GLM 4.7 Flash"
capabilities = ["text", "thinking", "thinking_toggle"]
capabilities = ["text", "thinking"]
[storage_size]
in_bytes = 19327352832
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
family = "glm"
quantization = "5bit"
base_model = "GLM 4.7 Flash"
capabilities = ["text", "thinking", "thinking_toggle"]
capabilities = ["text", "thinking"]
[storage_size]
in_bytes = 22548578304
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
family = "glm"
quantization = "6bit"
base_model = "GLM 4.7 Flash"
capabilities = ["text", "thinking", "thinking_toggle"]
capabilities = ["text", "thinking"]
[storage_size]
in_bytes = 26843545600
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
family = "glm"
quantization = "8bit"
base_model = "GLM 4.7 Flash"
capabilities = ["text", "thinking", "thinking_toggle"]
capabilities = ["text", "thinking"]
[storage_size]
in_bytes = 34359738368
@@ -1,12 +0,0 @@
model_id = "mlx-community/GLM-5-8bit-MXFP8"
n_layers = 78
hidden_size = 6144
supports_tensor = true
tasks = ["TextGeneration"]
family = "glm"
quantization = "8bit"
base_model = "GLM-5"
capabilities = ["text", "thinking"]
[storage_size]
in_bytes = 790517400864
@@ -1,12 +0,0 @@
model_id = "mlx-community/GLM-5-MXFP4-Q8"
n_layers = 78
hidden_size = 6144
supports_tensor = true
tasks = ["TextGeneration"]
family = "glm"
quantization = "MXFP4-Q8"
base_model = "GLM-5"
capabilities = ["text", "thinking"]
[storage_size]
in_bytes = 405478939008
@@ -1,12 +0,0 @@
model_id = "mlx-community/GLM-5"
n_layers = 78
hidden_size = 6144
supports_tensor = true
tasks = ["TextGeneration"]
family = "glm"
quantization = "bf16"
base_model = "GLM-5"
capabilities = ["text", "thinking"]
[storage_size]
in_bytes = 1487822475264
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
family = "kimi"
quantization = ""
base_model = "Kimi K2"
capabilities = ["text", "thinking", "thinking_toggle"]
capabilities = ["text", "thinking"]
[storage_size]
in_bytes = 706522120192
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
family = "kimi"
quantization = ""
base_model = "Kimi K2.5"
capabilities = ["text", "thinking", "thinking_toggle"]
capabilities = ["text", "thinking"]
[storage_size]
in_bytes = 662498705408
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
family = "minimax"
quantization = "3bit"
base_model = "MiniMax M2.1"
capabilities = ["text", "thinking", "thinking_toggle"]
capabilities = ["text", "thinking"]
[storage_size]
in_bytes = 100086644736
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
family = "minimax"
quantization = "8bit"
base_model = "MiniMax M2.1"
capabilities = ["text", "thinking", "thinking_toggle"]
capabilities = ["text", "thinking"]
[storage_size]
in_bytes = 242986745856
@@ -1,12 +0,0 @@
model_id = "mlx-community/MiniMax-M2.5-4bit"
n_layers = 62
hidden_size = 3072
supports_tensor = true
tasks = ["TextGeneration"]
family = "minimax"
quantization = "4bit"
base_model = "MiniMax M2.5"
capabilities = ["text", "thinking"]
[storage_size]
in_bytes = 128666664960
@@ -1,12 +0,0 @@
model_id = "mlx-community/MiniMax-M2.5-6bit"
n_layers = 62
hidden_size = 3072
supports_tensor = true
tasks = ["TextGeneration"]
family = "minimax"
quantization = "6bit"
base_model = "MiniMax M2.5"
capabilities = ["text", "thinking"]
[storage_size]
in_bytes = 185826705408
@@ -1,12 +0,0 @@
model_id = "mlx-community/MiniMax-M2.5-8bit"
n_layers = 62
hidden_size = 3072
supports_tensor = true
tasks = ["TextGeneration"]
family = "minimax"
quantization = "8bit"
base_model = "MiniMax M2.5"
capabilities = ["text", "thinking"]
[storage_size]
in_bytes = 242986745856
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
family = "qwen"
quantization = "4bit"
base_model = "Qwen3 0.6B"
capabilities = ["text", "thinking", "thinking_toggle"]
capabilities = ["text", "thinking"]
[storage_size]
in_bytes = 342884352
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
family = "qwen"
quantization = "8bit"
base_model = "Qwen3 0.6B"
capabilities = ["text", "thinking", "thinking_toggle"]
capabilities = ["text", "thinking"]
[storage_size]
in_bytes = 698351616
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
family = "qwen"
quantization = "4bit"
base_model = "Qwen3 235B"
capabilities = ["text", "thinking", "thinking_toggle"]
capabilities = ["text", "thinking"]
[storage_size]
in_bytes = 141733920768
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
family = "qwen"
quantization = "8bit"
base_model = "Qwen3 235B"
capabilities = ["text", "thinking", "thinking_toggle"]
capabilities = ["text", "thinking"]
[storage_size]
in_bytes = 268435456000
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
family = "qwen"
quantization = "4bit"
base_model = "Qwen3 30B"
capabilities = ["text", "thinking", "thinking_toggle"]
capabilities = ["text", "thinking"]
[storage_size]
in_bytes = 17612931072
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
family = "qwen"
quantization = "8bit"
base_model = "Qwen3 30B"
capabilities = ["text", "thinking", "thinking_toggle"]
capabilities = ["text", "thinking"]
[storage_size]
in_bytes = 33279705088
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
family = "qwen"
quantization = "4bit"
base_model = "Qwen3 Next 80B"
capabilities = ["text", "thinking", "thinking_toggle"]
capabilities = ["text", "thinking"]
[storage_size]
in_bytes = 47080074240
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
family = "qwen"
quantization = "8bit"
base_model = "Qwen3 Next 80B"
capabilities = ["text", "thinking", "thinking_toggle"]
capabilities = ["text", "thinking"]
[storage_size]
in_bytes = 88814387200
@@ -1,12 +0,0 @@
model_id = "mlx-community/Step-3.5-Flash-4bit"
n_layers = 45
hidden_size = 4096
supports_tensor = true
tasks = ["TextGeneration"]
family = "step"
quantization = "4bit"
base_model = "Step 3.5 Flash"
capabilities = ["text", "thinking", "thinking_toggle"]
[storage_size]
in_bytes = 114572190076
@@ -1,12 +0,0 @@
model_id = "mlx-community/Step-3.5-Flash-6bit"
n_layers = 45
hidden_size = 4096
supports_tensor = true
tasks = ["TextGeneration"]
family = "step"
quantization = "6bit"
base_model = "Step 3.5 Flash"
capabilities = ["text", "thinking", "thinking_toggle"]
[storage_size]
in_bytes = 159039627774

Some files were not shown because too many files have changed in this diff Show More