move chunks to core
This commit is contained in:
+5
-4
@@ -47,8 +47,8 @@ dev = [
|
||||
]
|
||||
|
||||
[project.optional-dependencies]
|
||||
mlx = ["mlx_runner"]
|
||||
cuda = ["vllm_runner; sys_platform == 'linux' and platform_machine == 'aarch64'"]
|
||||
mlx = ["mlx_engine"]
|
||||
cuda = ["vllm_engine; sys_platform == 'linux' and platform_machine == 'aarch64'"]
|
||||
|
||||
###
|
||||
# workspace configuration
|
||||
@@ -63,8 +63,9 @@ members = [
|
||||
|
||||
[tool.uv.sources]
|
||||
exo_pyo3_bindings = { workspace = true }
|
||||
mlx_runner = { path = "python/mlx_runner" }
|
||||
vllm_runner = { path = "python/vllm_runner" }
|
||||
exo_core = { workspace = true }
|
||||
mlx_engine = { path = "python/mlx_engine" }
|
||||
vllm_engine = { path = "python/vllm_engine" }
|
||||
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/rltakashige/mlx-lm", branch = "leo/eval-left-padding-in-batched-rotation" }
|
||||
# Uncomment to use local mlx/mlx-lm development versions:
|
||||
|
||||
@@ -7,7 +7,9 @@ authors = [
|
||||
{ name = "Evan", email = "[email protected]" }
|
||||
]
|
||||
requires-python = ">=3.13"
|
||||
dependencies = []
|
||||
dependencies = [
|
||||
"pydantic",
|
||||
]
|
||||
|
||||
[build-system]
|
||||
requires = ["uv_build>=0.9.24,<0.10.0"]
|
||||
|
||||
@@ -9,8 +9,8 @@ from exo.api.types import (
|
||||
TopLogprobItem,
|
||||
Usage,
|
||||
)
|
||||
from exo.shared.models.model_cards import ModelId
|
||||
from exo.utils.pydantic_ext import TaggedModel
|
||||
from exo_core.model_cards import ModelId
|
||||
from exo_core.pydantic import TaggedModel
|
||||
|
||||
from .common import CommandId
|
||||
|
||||
@@ -4,7 +4,7 @@ from uuid import uuid4
|
||||
from pydantic import GetCoreSchemaHandler, field_validator
|
||||
from pydantic_core import core_schema
|
||||
|
||||
from exo.utils.pydantic_ext import CamelCaseModel
|
||||
from exo_core.pydantic import CamelCaseModel
|
||||
|
||||
|
||||
class Id(str):
|
||||
+2
-2
@@ -2,10 +2,10 @@ from enum import Enum
|
||||
|
||||
from pydantic import model_validator
|
||||
|
||||
from exo.shared.models.model_cards import ModelTask
|
||||
from exo_core.model_cards import ModelTask
|
||||
from exo.shared.types.common import Host, Id, NodeId
|
||||
from exo.shared.types.worker.runners import RunnerId, ShardAssignments, ShardMetadata
|
||||
from exo.utils.pydantic_ext import CamelCaseModel, TaggedModel
|
||||
from exo_core.pydantic_ext import CamelCaseModel, TaggedModel
|
||||
|
||||
|
||||
class InstanceId(Id):
|
||||
+4
-4
@@ -2,10 +2,10 @@ from collections.abc import Mapping
|
||||
|
||||
from pydantic import model_validator
|
||||
|
||||
from exo.shared.models.model_cards import ModelId
|
||||
from exo.shared.types.common import Id, NodeId
|
||||
from exo.shared.types.worker.shards import ShardMetadata
|
||||
from exo.utils.pydantic_ext import CamelCaseModel, TaggedModel
|
||||
from exo_core.model_cards import ModelId
|
||||
from exo_core.types.common import Id, NodeId
|
||||
from exo_core.types.shards import ShardMetadata
|
||||
from exo_core.pydantic import CamelCaseModel, TaggedModel
|
||||
|
||||
|
||||
class RunnerId(Id):
|
||||
+2
-2
@@ -3,8 +3,8 @@ from typing import TypeAlias, final
|
||||
|
||||
from pydantic import Field
|
||||
|
||||
from exo.shared.models.model_cards import ModelCard
|
||||
from exo.utils.pydantic_ext import TaggedModel
|
||||
from exo_core.model_cards import ModelCard
|
||||
from exo_core.pydantic import TaggedModel
|
||||
|
||||
|
||||
class Sharding(str, Enum):
|
||||
@@ -6,12 +6,12 @@ from exo.api.types import (
|
||||
ImageEditsTaskParams,
|
||||
ImageGenerationTaskParams,
|
||||
)
|
||||
from exo.shared.types.common import CommandId, Id
|
||||
from exo.shared.types.text_generation import TextGenerationTaskParams
|
||||
from exo.shared.types.worker.instances import BoundInstance, InstanceId
|
||||
from exo.shared.types.worker.runners import RunnerId
|
||||
from exo.shared.types.worker.shards import ShardMetadata
|
||||
from exo.utils.pydantic_ext import TaggedModel
|
||||
from exo_core.types.common import CommandId, Id
|
||||
from exo_core.types.text_generation import TextGenerationTaskParams
|
||||
from exo_core.types.instances import BoundInstance, InstanceId
|
||||
from exo_core.types.runners import RunnerId
|
||||
from exo_core.types.shards import ShardMetadata
|
||||
from exo_core.pydantic import TaggedModel
|
||||
|
||||
|
||||
class TaskId(Id):
|
||||
+1
-1
@@ -8,7 +8,7 @@ from typing import Any, Literal
|
||||
|
||||
from pydantic import BaseModel
|
||||
|
||||
from exo.shared.types.common import ModelId
|
||||
from exo_core.types.common import ModelId
|
||||
|
||||
MessageRole = Literal["user", "assistant", "system", "developer"]
|
||||
ReasoningEffort = Literal["none", "minimal", "low", "medium", "high", "xhigh"]
|
||||
@@ -1,7 +1,7 @@
|
||||
from math import ceil
|
||||
from typing import Self, overload
|
||||
|
||||
from exo.utils.pydantic_ext import FrozenModel
|
||||
from exo_core.pydantic import FrozenModel
|
||||
|
||||
|
||||
class Memory(FrozenModel):
|
||||
@@ -1,5 +1,5 @@
|
||||
[project]
|
||||
name = "vllm-runner"
|
||||
name = "vllm-engine"
|
||||
version = "0.1.0"
|
||||
description = "Add your description here"
|
||||
readme = "README.md"
|
||||
|
||||
Reference in New Issue
Block a user