vllm/pyproject.toml
Adrian Abeyta 2ff767b513
Enable scaled FP8 (e4m3fn) KV cache on ROCm (AMD GPU) (#3290)
Co-authored-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
Co-authored-by: HaiShaw <hixiao@gmail.com>
Co-authored-by: AdrianAbeyta <Adrian.Abeyta@amd.com>
Co-authored-by: Matthew Wong <Matthew.Wong2@amd.com>
Co-authored-by: root <root@gt-pla-u18-08.pla.dcgpu>
Co-authored-by: mawong-amd <156021403+mawong-amd@users.noreply.github.com>
Co-authored-by: ttbachyinsda <ttbachyinsda@outlook.com>
Co-authored-by: guofangze <guofangze@kuaishou.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: jacobthebanana <50071502+jacobthebanana@users.noreply.github.com>
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2024-04-03 14:15:55 -07:00

62 lines
1.1 KiB
TOML

[build-system]
# Should be mirrored in requirements-build.txt
requires = [
"cmake>=3.21",
"ninja",
"packaging",
"setuptools >= 49.4.0",
"torch == 2.1.2",
"wheel",
]
build-backend = "setuptools.build_meta"
[tool.ruff]
# Allow lines to be as long as 80.
line-length = 80
exclude = [
# External file, leaving license intact
"examples/fp8/quantizer/quantize.py"
]
[tool.ruff.lint]
select = [
# pycodestyle
"E",
# Pyflakes
"F",
# pyupgrade
# "UP",
# flake8-bugbear
"B",
# flake8-simplify
"SIM",
# isort
# "I",
]
ignore = [
# star imports
"F405", "F403",
# lambda expression assignment
"E731",
# Loop control variable not used within loop body
"B007",
]
[tool.mypy]
python_version = "3.8"
ignore_missing_imports = true
files = "vllm"
# TODO(woosuk): Include the code from Megatron and HuggingFace.
exclude = "vllm/model_executor/parallel_utils/|vllm/model_executor/models/"
[tool.codespell]
ignore-words-list = "dout, te, indicies"
skip = "./tests/prompts,./benchmarks/sonnet.txt"
[tool.isort]
use_parentheses = true
skip_gitignore = true