Files
exo/pyproject.toml
T
Ryuichi Leo Takashige 01701ca609 try using different fork
2026-03-16 17:05:17 +00:00

174 lines
4.2 KiB
TOML

[project]
name = "exo"
version = "0.3.68"
description = "Exo"
readme = "README.md"
requires-python = ">=3.13"
dependencies = [
"aiofiles>=24.1.0",
"aiohttp>=3.12.14",
"types-aiofiles>=24.1.0.20250708",
"pydantic>=2.11.7",
"fastapi>=0.116.1",
"filelock>=3.18.0",
"rustworkx>=0.17.1",
"huggingface-hub>=0.33.4",
"psutil>=7.0.0",
"loguru>=0.7.3",
"exo_pyo3_bindings", # rust bindings
"anyio==4.11.0",
"mlx; sys_platform == 'darwin'",
"mlx==0.30.6; sys_platform == 'linux'",
"mlx-lm",
"tiktoken>=0.12.0", # required for kimi k2 tokenizer
"hypercorn>=0.18.0",
"openai-harmony>=0.0.8",
"httpx>=0.28.1",
"tomlkit>=0.14.0",
"pillow>=11.0,<12.0", # compatibility with mflux
"mflux==0.15.5; sys_platform == 'darwin'",
"python-multipart>=0.0.21",
"msgspec>=0.19.0",
"zstandard>=0.23.0",
]
[project.scripts]
exo = "exo.main:main"
# dependencies only required for development
[dependency-groups]
dev = [
"basedpyright>=1.29.0",
"pyinstaller>=6.17.0",
"pytest>=8.4.0",
"pytest-asyncio>=1.0.0",
"pytest-env",
"ruff>=0.11.13",
]
[project.optional-dependencies]
cuda = [
"torch>=2.10.0; sys_platform == 'linux'",
"vllm>=0.13.0; sys_platform == 'linux'",
"mlx-cuda-13==0.30.6; sys_platform == 'linux'",
"fastsafetensors>=0.1.10; sys_platform == 'linux'",
]
###
# workspace configuration
###
[tool.uv.workspace]
members = ["rust/exo_pyo3_bindings", "bench"]
[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/rltakashige/mlx-lm", branch = "leo/eval-left-padding-in-batched-rotation" }
torch = [{ index = "pytorch-cu130", marker = "sys_platform == 'linux'" }]
vllm = { git = "https://github.com/rltakashige/vllm-transformers-sm121.git" }
# Uncomment to use local mlx/mlx-lm development versions:
# mlx = { path = "/Users/Shared/mlx", editable=true }
# mlx-lm = { path = "/Users/Shared/mlx-lm", editable=true }
[[tool.uv.index]]
name = "pytorch-cu130"
url = "https://download.pytorch.org/whl/cu130"
explicit = true
[build-system]
requires = ["uv_build>=0.8.9,<0.9.0"]
build-backend = "uv_build"
###
# type-checker configuration
###
[tool.basedpyright]
include = [".venv/lib/mlx", ".venv/lib/mlx_lm", "src", "bench"]
typeCheckingMode = "strict"
failOnWarnings = true
reportAny = "error"
reportUnknownVariableType = "error"
reportUnknownParameterType = "error"
reportMissingParameterType = "error"
reportMissingTypeStubs = "error"
reportInvalidCast = "error"
reportUnnecessaryCast = "error"
reportUnnecessaryTypeIgnoreComment = "error"
pythonVersion = "3.13"
pythonPlatform = "Darwin"
exclude = [
"**/.venv",
"**/venv",
"**/__pycache__",
"**/exo_scripts",
"**/.direnv",
"**/rust",
"**/.github",
"**/vllm_patches",
"**/engines/vllm",
]
stubPath = ".mlx_typings"
extraPaths = [".cuda_typings"]
[[tool.basedpyright.executionEnvironments]]
root = "src/exo/worker/runner/vllm_inference"
extraPaths = ["src", ".cuda_typings"]
reportMissingModuleSource = false
[[tool.basedpyright.executionEnvironments]]
root = "src"
###
# uv configuration
###
# supported platforms for this project
[tool.uv]
required-version = ">=0.8.6"
prerelease = "allow"
environments = [
"sys_platform == 'darwin'",
"sys_platform == 'linux' and platform_machine == 'aarch64'",
]
no-binary-package = ["vllm"]
no-build-isolation-package = ["vllm"]
extra-build-dependencies = { vllm = [
"cmake>=3.26.1",
"ninja",
"packaging>=24.2",
"setuptools>=77.0.3,<81.0.0",
"setuptools-scm>=8.0",
"wheel",
"jinja2",
] }
conflicts = [[{ package = "exo", extra = "cuda" }, { package = "exo-bench" }]]
###
# ruff configuration
###
[tool.ruff]
extend-exclude = [
"shared/protobufs/**",
"*mlx_typings/**",
"*cuda_typings/**",
"rust/exo_pyo3_bindings/**",
"bench/vendor/**",
]
[tool.ruff.lint]
extend-select = ["I", "N", "B", "A", "PIE", "SIM"]
[tool.pytest.ini_options]
pythonpath = "."
asyncio_mode = "auto"
markers = ["slow: marks tests as slow (deselected by default)"]
env = ["EXO_TESTS=1"]
addopts = "-m 'not slow' --ignore=tests/start_distributed_test.py"
filterwarnings = ["ignore:builtin type Swig:DeprecationWarning"]