pyproject.toml

[build-system]
# Should be mirrored in requirements/build.txt
requires = [
    "cmake>=3.26",
    "ninja",
    "packaging>=24.2",
    "setuptools>=77.0.3,<80.0.0",
    "setuptools-scm>=8.0",
    "torch == 2.7.0",
    "wheel",
    "jinja2",
]
build-backend = "setuptools.build_meta"

[project]
name = "vllm"
authors = [{name = "vLLM Team"}]
license = "Apache-2.0"
license-files = ["LICENSE"]
readme = "README.md"
description = "A high-throughput and memory-efficient inference and serving engine for LLMs"
classifiers = [
    "Programming Language :: Python :: 3.9",
    "Programming Language :: Python :: 3.10",
    "Programming Language :: Python :: 3.11",
    "Programming Language :: Python :: 3.12",
    "Intended Audience :: Developers",
    "Intended Audience :: Information Technology",
    "Intended Audience :: Science/Research",
    "Topic :: Scientific/Engineering :: Artificial Intelligence",
    "Topic :: Scientific/Engineering :: Information Analysis",
]
requires-python = ">=3.9,<3.13"
dynamic = [ "version", "dependencies", "optional-dependencies"]

[project.urls]
Homepage="https://github.com/vllm-project/vllm"
Documentation="https://vllm.readthedocs.io/en/latest/"
Slack="http://slack.vllm.ai/"

[project.scripts]
vllm = "vllm.entrypoints.cli.main:main"

[project.entry-points."vllm.general_plugins"]
lora_filesystem_resolver = "vllm.plugins.lora_resolvers.filesystem_resolver:register_filesystem_resolver"

[tool.setuptools_scm]
# no extra settings needed, presence enables setuptools-scm

[tool.setuptools.packages.find]
where = ["."]
include = ["vllm*"]

[tool.yapfignore]
ignore_patterns = [
    "build/**",
]

[tool.ruff]
# Allow lines to be as long as 80.
line-length = 80
exclude = [
    # External file, leaving license intact
    "examples/other/fp8/quantizer/quantize.py",
    "vllm/vllm_flash_attn/flash_attn_interface.pyi"
]

[tool.ruff.lint.per-file-ignores]
"vllm/third_party/**" = ["ALL"]
"vllm/version.py" = ["F401"]
"vllm/_version.py" = ["ALL"]
# Python 3.8 typing. TODO: Remove these excludes after v1.0.0
"vllm/adapter_commons/**/*.py" = ["UP006", "UP035"]
"vllm/attention/**/*.py" = ["UP006", "UP035"]
"vllm/compilation/**/*.py" = ["UP006", "UP035"]
"vllm/core/**/*.py" = ["UP006", "UP035"]
"vllm/device_allocator/**/*.py" = ["UP006", "UP035"]
"vllm/distributed/**/*.py" = ["UP006", "UP035"]
"vllm/engine/**/*.py" = ["UP006", "UP035"]
"vllm/executor/**/*.py" = ["UP006", "UP035"]
"vllm/lora/**/*.py" = ["UP006", "UP035"]
"vllm/model_executor/layers/**/*.py" = ["UP006", "UP035"]
"vllm/model_executor/model_loader/**/*.py" = ["UP006", "UP035"]
"vllm/model_executor/models/**/*.py" = ["UP006", "UP035"]
"vllm/platforms/**/*.py" = ["UP006", "UP035"]
"vllm/plugins/**/*.py" = ["UP006", "UP035"]
"vllm/profiler/**/*.py" = ["UP006", "UP035"]
"vllm/prompt_adapter/**/*.py" = ["UP006", "UP035"]
"vllm/spec_decode/**/*.py" = ["UP006", "UP035"]
"vllm/transformers_utils/**/*.py" = ["UP006", "UP035"]
"vllm/triton_utils/**/*.py" = ["UP006", "UP035"]
"vllm/vllm_flash_attn/**/*.py" = ["UP006", "UP035"]
"vllm/worker/**/*.py" = ["UP006", "UP035"]
"vllm/utils.py" = ["UP006", "UP035"]

[tool.ruff.lint]
select = [
    # pycodestyle
    "E",
    # Pyflakes
    "F",
    # pyupgrade
    "UP",
    # flake8-bugbear
    "B",
    # flake8-simplify
    "SIM",
    # isort
    # "I",
    "G",
]
ignore = [
    # star imports
    "F405", "F403",
    # lambda expression assignment
    "E731",
    # Loop control variable not used within loop body
    "B007",
    # f-string format
    "UP032",
    # Can remove once 3.10+ is the minimum Python version
    "UP007",
]

[tool.mypy]
ignore_missing_imports = true
check_untyped_defs = true
follow_imports = "silent"

# After fixing type errors resulting from follow_imports: "skip" -> "silent",
# move the directory here and remove it from tools/mypy.sh
files = [
    "vllm/*.py",
    "vllm/adapter_commons",
    "vllm/assets",
    "vllm/entrypoints",
    "vllm/core",
    "vllm/inputs",
    "vllm/logging_utils",
    "vllm/multimodal",
    "vllm/platforms",
    "vllm/transformers_utils",
    "vllm/triton_utils",
    "vllm/usage",
]
# TODO(woosuk): Include the code from Megatron and HuggingFace.
exclude = [
    "vllm/model_executor/parallel_utils/|vllm/model_executor/models/",
    # Ignore triton kernels in ops.
    'vllm/attention/ops/.*\.py$'
]

[tool.codespell]
ignore-words-list = "dout, te, indicies, subtile, ElementE"
skip = "tests/models/fixtures/*,tests/prompts/*,benchmarks/sonnet.txt,tests/lora/data/*,build/*,vllm/third_party/*"

[tool.isort]
use_parentheses = true
skip_gitignore = true

[tool.pytest.ini_options]
markers = [
    "skip_global_cleanup",
    "core_model: enable this model test in each PR instead of only nightly",
    "cpu_model: enable this model test in CPU tests",
    "split: run this test as part of a split",
    "distributed: run this test only in distributed GPU tests",
    "skip_v1: do not run this test with v1",
    "optional: optional tests that are automatically skipped, include --optional to run them",
]

[tool.pymarkdown]
plugins.md004.style = "sublist" # ul-style
plugins.md013.enabled = false # line-length
plugins.md041.enabled = false # first-line-h1
plugins.md033.enabled = false # inline-html
plugins.md024.allow_different_nesting = true # no-duplicate-headers