pyproject.toml

[project]
name = "vec-inf"
version = "0.9.0"
description = "Efficient LLM inference on Slurm clusters using vLLM."
readme = "README.md"
authors = [{name = "Marshall Wang", email = "marshall.wang@vectorinstitute.ai"}]
license = "MIT"
requires-python = ">=3.10"
dependencies = [
    "requests>=2.31.0",
    "click>=8.1.0",
    "rich>=13.7.0",
    "pydantic>=2.10.6",
    "pyyaml>=6.0.2",
]

[dependency-groups]
dev = [
    "codecov>=2.1.13",
    "mypy>=1.15.0",
    "nbqa>=1.9.1",
    "openai>=1.65.1",
    "pip-audit>=2.8.0",
    "pre-commit>=4.1.0",
    "pytest>=8.3.4",
    "pytest-asyncio>=0.25.3",
    "pytest-cov>=6.0.0",
    "pytest-mock>=3.14.0",
    "ruff>=0.9.6",
]
docs = [
    "mkdocs>=1.5.3",
    "mkdocs-material>=9.5.12",
    "mkdocstrings>=0.24.1",
    "mkdocstrings-python>=1.8.0",
    "pymdown-extensions>=10.7.1",
    "mike>=2.0.0",
]
# Common inference dependencies (shared by both backends)
inference = [
    "xgrammar>=0.1.11",
    "torch>=2.7.0",
    "cupy-cuda12x>=12.3.0",
    "flashinfer-python>=0.4.0",
    "ax-platform>=1.1.0",
    "py3nvml",
    "wandb>=0.17.0",
]

[project.optional-dependencies]
# vLLM inference backend (conflicts with sglang due to dependency version conflicts)
# Install with: uv sync --extra vllm --group inference
vllm = [
    "vllm>=0.11.2",
    "ray[default]>=2.51.0",
    "vllm[audio]",
    "vllm[bench]",
    "torchcodec>=0.9.0,<0.10.0",
]
# SGLang inference backend (conflicts with vllm due to dependency version conflicts)
# Install with: uv sync --extra sglang --group inference
sglang = [
    "sglang>=0.5.5",
    "sgl_kernel>=0.3.0",
    "orjson>=3.11.0",
    "torchao>=0.9.0",
]

[tool.uv]
# Declare that vllm and sglang extras are mutually exclusive
# This prevents uv from trying to resolve both together in the lock file
conflicts = [
    [
        { extra = "vllm" },
        { extra = "sglang" },
    ],
]

[project.scripts]
vec-inf = "vec_inf.cli._cli:cli"

[build-system]
requires = ["hatchling"]
build-backend = "hatchling.build"

[tool.hatch.build.targets.wheel]
packages = ["vec_inf"]

[tool.mypy]
ignore_missing_imports = true
install_types = true
pretty = true
namespace_packages = true
explicit_package_bases = true
non_interactive = true
warn_unused_configs = true
allow_any_generics = false
allow_subclassing_any = false
allow_untyped_calls = false
allow_untyped_defs = false
allow_incomplete_defs = false
check_untyped_defs = true
allow_untyped_decorators = false
warn_redundant_casts = true
warn_unused_ignores = true
warn_return_any = true
implicit_reexport = false
strict_equality = true
extra_checks = true

[tool.ruff]
include = ["*.py", "pyproject.toml", "*.ipynb"]
line-length = 88

[tool.ruff.format]
quote-style = "double"
indent-style = "space"
docstring-code-format = true

[tool.ruff.lint]
select = [
    "A", # flake8-builtins
    "B", # flake8-bugbear
    "COM", # flake8-commas
    "C4", # flake8-comprehensions
    "RET", # flake8-return
    "SIM", # flake8-simplify
    "ICN", # flake8-import-conventions
    "Q", # flake8-quotes
    "RSE", # flake8-raise
    "D", # pydocstyle
    "E", # pycodestyle
    "F", # pyflakes
    "I", # isort
    "W", # pycodestyle
    "N", # pep8-naming
    "ERA", # eradicate
    "PL", # pylint
]
fixable = ["A", "B", "COM", "C4", "RET", "SIM", "ICN", "Q", "RSE", "D", "E", "F", "I", "W", "N", "ERA", "PL"]
ignore = [
    "B905", # `zip()` without an explicit `strict=` parameter
    "E501", # line too long
    "D203", # 1 blank line required before class docstring
    "D213", # Multi-line docstring summary should start at the second line
    "PLR2004", # Replace magic number with named constant
    "PLR0913", # Too many arguments
    "COM812", # Missing trailing comma
]

# Ignore import violations in all `__init__.py` files.
[tool.ruff.lint.per-file-ignores]
"__init__.py" = ["E402", "F401", "F403", "F811"]

[tool.ruff.lint.pep8-naming]
ignore-names = ["X*", "setUp"]

[tool.ruff.lint.isort]
lines-after-imports = 2

[tool.ruff.lint.pydocstyle]
convention = "numpy"

[tool.ruff.lint.pycodestyle]
max-doc-length = 88

[tool.pytest.ini_options]
markers = [
    "integration_test: marks tests as integration tests",
]

[tool.coverage]
    [tool.coverage.run]
    source=["vec_inf"]
    omit=["tests/*", "*__init__.py"]