135 lines
3.7 KiB
TOML
135 lines
3.7 KiB
TOML
[build-system]
|
|
requires = ["setuptools>=61.0", "wheel"]
|
|
build-backend = "setuptools.build_meta"
|
|
|
|
[project]
|
|
name = "sglang"
|
|
version = "0.4.4.post3"
|
|
description = "SGLang is yet another fast serving framework for large language models and vision language models."
|
|
readme = "README.md"
|
|
requires-python = ">=3.8"
|
|
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 = [
|
|
"compressed-tensors",
|
|
"datasets",
|
|
"decord",
|
|
"fastapi",
|
|
"hf_transfer",
|
|
"huggingface_hub",
|
|
"interegular",
|
|
"llguidance>=0.6.15",
|
|
"modelscope",
|
|
"ninja",
|
|
"orjson",
|
|
"packaging",
|
|
"pillow",
|
|
"prometheus-client>=0.20.0",
|
|
"psutil",
|
|
"pydantic",
|
|
"python-multipart",
|
|
"pyzmq>=25.1.2",
|
|
"soundfile==0.13.1",
|
|
"torchao>=0.7.0",
|
|
"transformers==4.50.0",
|
|
"uvicorn",
|
|
"uvloop",
|
|
"compressed-tensors",
|
|
"xgrammar==0.1.17",
|
|
]
|
|
|
|
srt = [
|
|
"sglang[runtime_common]",
|
|
"sgl-kernel==0.0.5.post4",
|
|
"flashinfer_python==0.2.3",
|
|
"torch==2.5.1",
|
|
"cuda-python",
|
|
"outlines>=0.0.44,<=0.1.11",
|
|
"partial_json_parser",
|
|
"einops",
|
|
]
|
|
|
|
# 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",
|
|
"vllm==0.6.7.dev2",
|
|
"outlines==0.1.11"
|
|
]
|
|
|
|
# xpu is not enabled in public vllm and torch whl,
|
|
# need to follow https://docs.vllm.ai/en/latest/getting_started/xpu-installation.htmlinstall vllm
|
|
srt_xpu = ["sglang[runtime_common]", "outlines>=0.0.44,<=0.1.11"]
|
|
|
|
# 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]", "outlines>=0.0.44,<=0.1.11"]
|
|
|
|
# CPU: currently, there are no pre-built vllm wheels for CPU.
|
|
# To install vllm for CPU, please follow the instruction here:
|
|
# https://docs.vllm.ai/en/latest/getting_started/installation/cpu/index.html
|
|
srt_cpu = ["sglang[runtime_common]", "outlines>=0.0.44,<=0.1.11", "torch"]
|
|
|
|
openai = ["openai>=1.0", "tiktoken"]
|
|
anthropic = ["anthropic>=0.20.0"]
|
|
litellm = ["litellm>=1.0.0"]
|
|
torch_memory_saver = ["torch_memory_saver>=0.0.4"]
|
|
test = [
|
|
"jsonlines",
|
|
"matplotlib",
|
|
"pandas",
|
|
"sentence_transformers",
|
|
"accelerate",
|
|
"peft",
|
|
]
|
|
all = ["sglang[srt]", "sglang[openai]", "sglang[anthropic]", "sglang[litellm]"]
|
|
all_hip = ["sglang[srt_hip]", "sglang[openai]", "sglang[anthropic]", "sglang[litellm]"]
|
|
all_xpu = ["sglang[srt_xpu]", "sglang[openai]", "sglang[anthropic]", "sglang[litellm]"]
|
|
all_hpu = ["sglang[srt_hpu]", "sglang[openai]", "sglang[anthropic]", "sglang[litellm]"]
|
|
all_cpu = ["sglang[srt_cpu]", "sglang[openai]", "sglang[anthropic]", "sglang[litellm]"]
|
|
|
|
dev = ["sglang[all]", "sglang[test]"]
|
|
dev_hip = ["sglang[all_hip]", "sglang[test]"]
|
|
dev_xpu = ["sglang[all_xpu]", "sglang[test]"]
|
|
dev_hpu = ["sglang[all_hpu]", "sglang[test]"]
|
|
dev_cpu = ["sglang[all_cpu]", "sglang[test]"]
|
|
|
|
[project.urls]
|
|
"Homepage" = "https://github.com/sgl-project/sglang"
|
|
"Bug Tracker" = "https://github.com/sgl-project/sglang/issues"
|
|
|
|
[tool.setuptools.package-data]
|
|
"sglang" = [
|
|
"srt/layers/moe/fused_moe_triton/configs/*.json",
|
|
"srt/layers/quantization/configs/*.json",
|
|
]
|
|
|
|
[tool.setuptools.packages.find]
|
|
exclude = [
|
|
"assets*",
|
|
"benchmark*",
|
|
"docs*",
|
|
"dist*",
|
|
"playground*",
|
|
"scripts*",
|
|
"tests*",
|
|
]
|
|
|
|
[tool.wheel]
|
|
exclude = [
|
|
"assets*",
|
|
"benchmark*",
|
|
"docs*",
|
|
"dist*",
|
|
"playground*",
|
|
"scripts*",
|
|
"tests*",
|
|
]
|