mirror of
https://github.com/kvcache-ai/sglang.git
synced 2026-06-30 19:57:52 +00:00
69eb95f20c
Co-authored-by: HAI <hixiao@gmail.com> Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
221 lines
4.5 KiB
TOML
Executable File
221 lines
4.5 KiB
TOML
Executable File
[build-system]
|
|
requires = ["setuptools>=61.0", "setuptools-scm>=8.0", "wheel"]
|
|
build-backend = "setuptools.build_meta"
|
|
|
|
[project]
|
|
name = "sglang"
|
|
dynamic = ["version"]
|
|
description = "SGLang is a fast serving framework for large language models and vision language models."
|
|
readme = "README.md"
|
|
requires-python = ">=3.10"
|
|
license = { file = "LICENSE" }
|
|
classifiers = [
|
|
"Programming Language :: Python :: 3",
|
|
"License :: OSI Approved :: Apache Software License",
|
|
]
|
|
dependencies = ["aiohttp", "requests", "tqdm", "numpy", "IPython", "setproctitle"]
|
|
|
|
[project.optional-dependencies]
|
|
runtime_common = [
|
|
"IPython",
|
|
"aiohttp",
|
|
"anthropic>=0.20.0",
|
|
"blobfile==3.0.0",
|
|
"av",
|
|
"build",
|
|
"compressed-tensors",
|
|
"datasets",
|
|
"easydict",
|
|
"einops",
|
|
"fastapi",
|
|
"gguf",
|
|
"interegular",
|
|
"llguidance>=0.7.11,<0.8.0",
|
|
"modelscope",
|
|
"msgspec",
|
|
"ninja",
|
|
"numpy",
|
|
"openai-harmony==0.0.4",
|
|
"openai==2.6.1",
|
|
"orjson",
|
|
"outlines==0.1.11",
|
|
"packaging",
|
|
"partial_json_parser",
|
|
"pillow",
|
|
"prometheus-client>=0.20.0",
|
|
"psutil",
|
|
"py-spy",
|
|
"pybase64",
|
|
"pydantic",
|
|
"python-multipart",
|
|
"pyzmq>=25.1.2",
|
|
"requests",
|
|
"scipy",
|
|
"sentencepiece",
|
|
"setproctitle",
|
|
"soundfile==0.13.1",
|
|
"tiktoken",
|
|
"timm==1.0.16",
|
|
"torchao==0.9.0",
|
|
"tqdm",
|
|
"mistral_common>=1.11.0",
|
|
"transformers==5.5.4",
|
|
"uvicorn",
|
|
"uvloop",
|
|
"xgrammar==0.1.32",
|
|
"smg-grpc-servicer>=0.5.0",
|
|
]
|
|
|
|
diffusion_common = [
|
|
"PyYAML==6.0.1",
|
|
"cloudpickle",
|
|
"diffusers==0.37.0",
|
|
"imageio==2.36.0",
|
|
"imageio-ffmpeg==0.5.1",
|
|
"moviepy>=2.0.0",
|
|
"opencv-python-headless==4.10.0.84",
|
|
"remote-pdb",
|
|
"addict",
|
|
"scikit-image==0.25.2",
|
|
"trimesh>=4.0.0",
|
|
"xatlas",
|
|
]
|
|
|
|
tracing = [
|
|
"opentelemetry-sdk",
|
|
"opentelemetry-api",
|
|
"opentelemetry-exporter-otlp",
|
|
"opentelemetry-exporter-otlp-proto-grpc",
|
|
]
|
|
|
|
# HIP (Heterogeneous-computing Interface for Portability) for AMD
|
|
# => base docker rocm/vllm-dev:20250114, not from public vllm whl
|
|
srt_hip = [
|
|
"sglang[runtime_common]",
|
|
"torch",
|
|
"petit_kernel==0.0.2",
|
|
"wave-lang==3.8.2",
|
|
]
|
|
|
|
diffusion_hip = [
|
|
"sglang[diffusion_common]",
|
|
"peft>=0.18.0,<0.19.0", # Pin to <0.19.0 due to torchao incompatibility
|
|
"st_attn==0.0.7",
|
|
"vsa==0.0.4",
|
|
"runai_model_streamer>=0.15.5",
|
|
"cache-dit==1.1.8",
|
|
]
|
|
|
|
# For Intel Gaudi(device : hpu) follow the installation guide
|
|
# https://docs.vllm.ai/en/latest/getting_started/gaudi-installation.html
|
|
srt_hpu = ["sglang[runtime_common]"]
|
|
|
|
# https://docs.sglang.io/platforms/mthreads_gpu.md
|
|
srt_musa = [
|
|
"sglang[runtime_common]",
|
|
"torch",
|
|
"torch_musa",
|
|
"torchada>=0.1.48",
|
|
"mthreads-ml-py",
|
|
"mate",
|
|
"mate-deep_gemm",
|
|
"mate-flash-attention",
|
|
"numpy<2.0",
|
|
]
|
|
|
|
diffusion_musa = [
|
|
"sglang[diffusion_common]",
|
|
"st_attn==0.0.7",
|
|
"vsa==0.0.4",
|
|
"runai_model_streamer>=0.15.5",
|
|
"cache-dit==1.1.8",
|
|
]
|
|
|
|
# https://docs.sglang.io/platforms/mps.md
|
|
srt_mps = [
|
|
"sglang[runtime_common]",
|
|
"torch==2.9.1",
|
|
"torchao==0.9.0",
|
|
"torchaudio==2.9.1",
|
|
"torchvision",
|
|
"mlx",
|
|
"mlx-lm",
|
|
]
|
|
|
|
diffusion_mps = [
|
|
"sglang[diffusion_common]",
|
|
"cloudpickle==3.1.2",
|
|
"remote-pdb==2.1.0",
|
|
"cache-dit==1.2.3",
|
|
"addict==2.4.0",
|
|
"av==16.1.0",
|
|
"scikit-image==0.25.2",
|
|
"trimesh>=4.0.0",
|
|
"xatlas",
|
|
]
|
|
|
|
test = [
|
|
"accelerate",
|
|
"expecttest",
|
|
"gguf",
|
|
"jsonlines",
|
|
"matplotlib",
|
|
"pandas",
|
|
"peft>=0.18.0,<0.19.0", # Pin to <0.19.0 due to torchao incompatibility
|
|
"pytest",
|
|
"sentence_transformers",
|
|
"tabulate",
|
|
]
|
|
|
|
all_hip = ["sglang[srt_hip]", "sglang[diffusion_hip]"]
|
|
all_hpu = ["sglang[srt_hpu]"]
|
|
all_musa = ["sglang[srt_musa]", "sglang[diffusion_musa]"]
|
|
all_mps = ["sglang[srt_mps]", "sglang[diffusion_mps]"]
|
|
|
|
dev_hip = ["sglang[all_hip]", "sglang[test]"]
|
|
dev_hpu = ["sglang[all_hpu]", "sglang[test]"]
|
|
dev_musa = ["sglang[all_musa]", "sglang[test]"]
|
|
dev_mps = ["sglang[all_mps]", "sglang[test]"]
|
|
|
|
[project.urls]
|
|
"Homepage" = "https://github.com/sgl-project/sglang"
|
|
"Bug Tracker" = "https://github.com/sgl-project/sglang/issues"
|
|
|
|
[project.scripts]
|
|
sglang = "sglang.cli.main:main"
|
|
|
|
[tool.setuptools.package-data]
|
|
"sglang" = [
|
|
"srt/**/*",
|
|
"jit_kernel/**/*"
|
|
]
|
|
|
|
[tool.setuptools.packages.find]
|
|
exclude = [
|
|
"assets*",
|
|
"benchmark*",
|
|
"docs*",
|
|
"dist*",
|
|
"playground*",
|
|
"scripts*",
|
|
"tests*",
|
|
]
|
|
|
|
[tool.wheel]
|
|
exclude = [
|
|
"assets*",
|
|
"benchmark*",
|
|
"docs*",
|
|
"dist*",
|
|
"playground*",
|
|
"scripts*",
|
|
"tests*",
|
|
]
|
|
|
|
[tool.setuptools_scm]
|
|
root = ".."
|
|
version_file = "sglang/_version.py"
|
|
git_describe_command = ["python3", "python/tools/get_version_tag.py"]
|
|
# Allow editable installs even when .git metadata is not available.
|
|
fallback_version = "0.0.0.dev0"
|