178 lines
5.2 KiB
TOML
178 lines
5.2 KiB
TOML
[build-system]
|
|
# Should be mirrored in requirements-build.txt
|
|
requires = [
|
|
"cmake>=3.26",
|
|
"ninja",
|
|
"packaging",
|
|
"setuptools>=61",
|
|
"setuptools-scm>=8.0",
|
|
"torch == 2.5.1",
|
|
"wheel",
|
|
"jinja2",
|
|
]
|
|
build-backend = "setuptools.build_meta"
|
|
|
|
[project]
|
|
name = "vllm"
|
|
authors = [{name = "vLLM Team"}]
|
|
license = { "file"= "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",
|
|
"License :: OSI Approved :: Apache Software License",
|
|
"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"
|
|
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"
|
|
|
|
[tool.setuptools_scm]
|
|
# no extra settings needed, presence enables setuptools-scm
|
|
|
|
[tool.setuptools.packages.find]
|
|
where = ["."]
|
|
exclude = ["benchmarks", "csrc", "docs", "examples", "tests*"]
|
|
namespaces = false
|
|
|
|
[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"
|
|
]
|
|
|
|
[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/inputs/**/*.py" = ["UP006", "UP035"]
|
|
"vllm/logging_utils/**/*.py" = ["UP006", "UP035"]
|
|
"vllm/lora/**/*.py" = ["UP006", "UP035"]
|
|
"vllm/model_executor/**/*.py" = ["UP006", "UP035"]
|
|
"vllm/multimodal/**/*.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/usage/**/*.py" = ["UP006", "UP035"]
|
|
"vllm/vllm_flash_attn/**/*.py" = ["UP006", "UP035"]
|
|
"vllm/assets/**/*.py" = ["UP006", "UP035"]
|
|
"vllm/worker/**/*.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",
|
|
"quant_model: run this model test under Quantized category",
|
|
"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
|