feat: support pip install sglang (#10465)
This commit is contained in:
Yineng Zhang
@@ -10,131 +10,87 @@ readme = "README.md"
|
||||
requires-python = ">=3.10"
|
||||
license = { file = "LICENSE" }
|
||||
classifiers = [
|
||||
"Programming Language :: Python :: 3",
|
||||
"License :: OSI Approved :: Apache Software License",
|
||||
"Programming Language :: Python :: 3",
|
||||
"License :: OSI Approved :: Apache Software License",
|
||||
]
|
||||
dependencies = [
|
||||
"aiohttp",
|
||||
"requests",
|
||||
"tqdm",
|
||||
"numpy",
|
||||
"IPython",
|
||||
"setproctitle",
|
||||
"blobfile==3.0.0",
|
||||
"build",
|
||||
"compressed-tensors",
|
||||
"datasets",
|
||||
"einops",
|
||||
"fastapi",
|
||||
"hf_transfer",
|
||||
"huggingface_hub",
|
||||
"interegular",
|
||||
"llguidance>=0.7.11,<0.8.0",
|
||||
"modelscope",
|
||||
"msgspec",
|
||||
"ninja",
|
||||
"openai==1.99.1",
|
||||
"openai-harmony==0.0.4",
|
||||
"orjson",
|
||||
"outlines==0.1.11",
|
||||
"packaging",
|
||||
"partial_json_parser",
|
||||
"pillow",
|
||||
"prometheus-client>=0.20.0",
|
||||
"psutil",
|
||||
"pybase64",
|
||||
"pydantic",
|
||||
"pynvml",
|
||||
"python-multipart",
|
||||
"pyzmq>=25.1.2",
|
||||
"scipy",
|
||||
"sentencepiece",
|
||||
"soundfile==0.13.1",
|
||||
"timm==1.0.16",
|
||||
"tiktoken",
|
||||
"torchao==0.9.0",
|
||||
"transformers==4.56.1",
|
||||
"uvicorn",
|
||||
"uvloop",
|
||||
"xgrammar==0.1.24",
|
||||
"sgl-kernel==0.3.9.post2",
|
||||
"torch==2.8.0",
|
||||
"torchaudio==2.8.0",
|
||||
"torchvision",
|
||||
"cuda-python",
|
||||
"flashinfer_python==0.3.1",
|
||||
"openai==1.99.1",
|
||||
"tiktoken",
|
||||
"anthropic>=0.20.0",
|
||||
"torch_memory_saver==0.0.8",
|
||||
"decord",
|
||||
]
|
||||
dependencies = ["aiohttp", "requests", "tqdm", "numpy", "IPython", "setproctitle"]
|
||||
|
||||
[project.optional-dependencies]
|
||||
runtime_common = [
|
||||
"blobfile==3.0.0",
|
||||
"build",
|
||||
"compressed-tensors",
|
||||
"datasets",
|
||||
"einops",
|
||||
"fastapi",
|
||||
"hf_transfer",
|
||||
"huggingface_hub",
|
||||
"interegular",
|
||||
"llguidance>=0.7.11,<0.8.0",
|
||||
"modelscope",
|
||||
"msgspec",
|
||||
"ninja",
|
||||
"openai==1.99.1",
|
||||
"openai-harmony==0.0.4",
|
||||
"orjson",
|
||||
"outlines==0.1.11",
|
||||
"packaging",
|
||||
"partial_json_parser",
|
||||
"pillow",
|
||||
"prometheus-client>=0.20.0",
|
||||
"psutil",
|
||||
"pybase64",
|
||||
"pydantic",
|
||||
"pynvml",
|
||||
"python-multipart",
|
||||
"pyzmq>=25.1.2",
|
||||
"scipy",
|
||||
"sentencepiece",
|
||||
"soundfile==0.13.1",
|
||||
"timm==1.0.16",
|
||||
"tiktoken",
|
||||
"torchao==0.9.0",
|
||||
"transformers==4.56.1",
|
||||
"uvicorn",
|
||||
"uvloop",
|
||||
"xgrammar==0.1.24",
|
||||
test = [
|
||||
"accelerate",
|
||||
"expecttest",
|
||||
"jsonlines",
|
||||
"matplotlib",
|
||||
"pandas",
|
||||
"peft",
|
||||
"sentence_transformers",
|
||||
"pytest",
|
||||
"tabulate",
|
||||
]
|
||||
|
||||
tracing = [
|
||||
"opentelemetry-sdk",
|
||||
"opentelemetry-api",
|
||||
"opentelemetry-exporter-otlp",
|
||||
"opentelemetry-exporter-otlp-proto-grpc",
|
||||
]
|
||||
|
||||
srt = [
|
||||
"sglang[runtime_common]",
|
||||
"sgl-kernel==0.3.9.post2",
|
||||
"torch==2.8.0",
|
||||
"torchaudio==2.8.0",
|
||||
"torchvision",
|
||||
"cuda-python",
|
||||
"flashinfer_python==0.3.1",
|
||||
]
|
||||
|
||||
blackwell = [
|
||||
"sglang[runtime_common]",
|
||||
"sgl-kernel==0.3.9.post2",
|
||||
"torch==2.8.0",
|
||||
"torchaudio==2.8.0",
|
||||
"torchvision",
|
||||
"cuda-python",
|
||||
"flashinfer_python==0.3.1",
|
||||
"nvidia-cutlass-dsl==4.1.0",
|
||||
]
|
||||
|
||||
# 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==3.7.0",
|
||||
]
|
||||
|
||||
# https://docs.sglang.ai/platforms/cpu_server.html
|
||||
srt_cpu = ["sglang[runtime_common]", "intel-openmp"]
|
||||
|
||||
# https://docs.sglang.ai/platforms/ascend_npu.html
|
||||
srt_npu = ["sglang[runtime_common]"]
|
||||
|
||||
# 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]"]
|
||||
|
||||
# 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]"]
|
||||
|
||||
openai = ["openai==1.99.1", "tiktoken"]
|
||||
anthropic = ["anthropic>=0.20.0"]
|
||||
litellm = ["litellm>=1.0.0"]
|
||||
torch_memory_saver = ["torch_memory_saver==0.0.8"]
|
||||
decord = ["decord"]
|
||||
test = [
|
||||
"accelerate",
|
||||
"expecttest",
|
||||
"jsonlines",
|
||||
"matplotlib",
|
||||
"pandas",
|
||||
"peft",
|
||||
"sentence_transformers",
|
||||
"pytest",
|
||||
"tabulate",
|
||||
]
|
||||
all = ["sglang[srt]", "sglang[openai]", "sglang[anthropic]", "sglang[torch_memory_saver]", "sglang[decord]"]
|
||||
all_hip = ["sglang[srt_hip]", "sglang[openai]", "sglang[anthropic]", "sglang[decord]"]
|
||||
all_xpu = ["sglang[srt_xpu]", "sglang[openai]", "sglang[anthropic]", "sglang[decord]"]
|
||||
all_hpu = ["sglang[srt_hpu]", "sglang[openai]", "sglang[anthropic]", "sglang[decord]"]
|
||||
all_cpu = ["sglang[srt_cpu]", "sglang[openai]", "sglang[anthropic]", "sglang[decord]"]
|
||||
all_npu = ["sglang[srt_npu]", "sglang[openai]", "sglang[anthropic]", "sglang[decord]"]
|
||||
|
||||
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]"]
|
||||
all = ["sglang[test]"]
|
||||
blackwell = ["nvidia-cutlass-dsl==4.1.0", "sglang[test]"]
|
||||
dev = ["sglang[test]"]
|
||||
|
||||
[project.urls]
|
||||
"Homepage" = "https://github.com/sgl-project/sglang"
|
||||
@@ -142,31 +98,31 @@ dev_cpu = ["sglang[all_cpu]", "sglang[test]"]
|
||||
|
||||
[tool.setuptools.package-data]
|
||||
"sglang" = [
|
||||
"srt/layers/moe/fused_moe_triton/configs/*/*.json",
|
||||
"srt/layers/quantization/configs/*.json",
|
||||
"srt/mem_cache/storage/hf3fs/hf3fs_utils.cpp",
|
||||
"srt/layers/moe/fused_moe_triton/configs/*/*.json",
|
||||
"srt/layers/quantization/configs/*.json",
|
||||
"srt/mem_cache/storage/hf3fs/hf3fs_utils.cpp",
|
||||
]
|
||||
|
||||
[tool.setuptools.packages.find]
|
||||
exclude = [
|
||||
"assets*",
|
||||
"benchmark*",
|
||||
"docs*",
|
||||
"dist*",
|
||||
"playground*",
|
||||
"scripts*",
|
||||
"tests*",
|
||||
"assets*",
|
||||
"benchmark*",
|
||||
"docs*",
|
||||
"dist*",
|
||||
"playground*",
|
||||
"scripts*",
|
||||
"tests*",
|
||||
]
|
||||
|
||||
[tool.wheel]
|
||||
exclude = [
|
||||
"assets*",
|
||||
"benchmark*",
|
||||
"docs*",
|
||||
"dist*",
|
||||
"playground*",
|
||||
"scripts*",
|
||||
"tests*",
|
||||
"assets*",
|
||||
"benchmark*",
|
||||
"docs*",
|
||||
"dist*",
|
||||
"playground*",
|
||||
"scripts*",
|
||||
"tests*",
|
||||
]
|
||||
|
||||
[tool.codespell]
|
||||
|
||||
174
python/pyproject_other.toml
Executable file
174
python/pyproject_other.toml
Executable file
@@ -0,0 +1,174 @@
|
||||
[build-system]
|
||||
requires = ["setuptools>=61.0", "wheel"]
|
||||
build-backend = "setuptools.build_meta"
|
||||
|
||||
[project]
|
||||
name = "sglang"
|
||||
version = "0.5.2"
|
||||
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 = [
|
||||
"blobfile==3.0.0",
|
||||
"build",
|
||||
"compressed-tensors",
|
||||
"datasets",
|
||||
"einops",
|
||||
"fastapi",
|
||||
"hf_transfer",
|
||||
"huggingface_hub",
|
||||
"interegular",
|
||||
"llguidance>=0.7.11,<0.8.0",
|
||||
"modelscope",
|
||||
"msgspec",
|
||||
"ninja",
|
||||
"openai==1.99.1",
|
||||
"openai-harmony==0.0.4",
|
||||
"orjson",
|
||||
"outlines==0.1.11",
|
||||
"packaging",
|
||||
"partial_json_parser",
|
||||
"pillow",
|
||||
"prometheus-client>=0.20.0",
|
||||
"psutil",
|
||||
"pybase64",
|
||||
"pydantic",
|
||||
"pynvml",
|
||||
"python-multipart",
|
||||
"pyzmq>=25.1.2",
|
||||
"scipy",
|
||||
"sentencepiece",
|
||||
"soundfile==0.13.1",
|
||||
"timm==1.0.16",
|
||||
"tiktoken",
|
||||
"torchao==0.9.0",
|
||||
"transformers==4.56.1",
|
||||
"uvicorn",
|
||||
"uvloop",
|
||||
"xgrammar==0.1.24",
|
||||
]
|
||||
|
||||
tracing = [
|
||||
"opentelemetry-sdk",
|
||||
"opentelemetry-api",
|
||||
"opentelemetry-exporter-otlp",
|
||||
"opentelemetry-exporter-otlp-proto-grpc",
|
||||
]
|
||||
|
||||
srt = [
|
||||
"sglang[runtime_common]",
|
||||
"sgl-kernel==0.3.9.post2",
|
||||
"torch==2.8.0",
|
||||
"torchaudio==2.8.0",
|
||||
"torchvision",
|
||||
"cuda-python",
|
||||
"flashinfer_python==0.3.1",
|
||||
]
|
||||
|
||||
blackwell = [
|
||||
"sglang[runtime_common]",
|
||||
"sgl-kernel==0.3.9.post2",
|
||||
"torch==2.8.0",
|
||||
"torchaudio==2.8.0",
|
||||
"torchvision",
|
||||
"cuda-python",
|
||||
"flashinfer_python==0.3.1",
|
||||
"nvidia-cutlass-dsl==4.1.0",
|
||||
]
|
||||
|
||||
# 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==3.7.0",
|
||||
]
|
||||
|
||||
# https://docs.sglang.ai/platforms/cpu_server.html
|
||||
srt_cpu = ["sglang[runtime_common]", "intel-openmp"]
|
||||
|
||||
# https://docs.sglang.ai/platforms/ascend_npu.html
|
||||
srt_npu = ["sglang[runtime_common]"]
|
||||
|
||||
# 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]"]
|
||||
|
||||
# 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]"]
|
||||
|
||||
openai = ["openai==1.99.1", "tiktoken"]
|
||||
anthropic = ["anthropic>=0.20.0"]
|
||||
litellm = ["litellm>=1.0.0"]
|
||||
torch_memory_saver = ["torch_memory_saver==0.0.8"]
|
||||
decord = ["decord"]
|
||||
test = [
|
||||
"accelerate",
|
||||
"expecttest",
|
||||
"jsonlines",
|
||||
"matplotlib",
|
||||
"pandas",
|
||||
"peft",
|
||||
"sentence_transformers",
|
||||
"pytest",
|
||||
"tabulate",
|
||||
]
|
||||
all = ["sglang[srt]", "sglang[openai]", "sglang[anthropic]", "sglang[torch_memory_saver]", "sglang[decord]"]
|
||||
all_hip = ["sglang[srt_hip]", "sglang[openai]", "sglang[anthropic]", "sglang[decord]"]
|
||||
all_xpu = ["sglang[srt_xpu]", "sglang[openai]", "sglang[anthropic]", "sglang[decord]"]
|
||||
all_hpu = ["sglang[srt_hpu]", "sglang[openai]", "sglang[anthropic]", "sglang[decord]"]
|
||||
all_cpu = ["sglang[srt_cpu]", "sglang[openai]", "sglang[anthropic]", "sglang[decord]"]
|
||||
all_npu = ["sglang[srt_npu]", "sglang[openai]", "sglang[anthropic]", "sglang[decord]"]
|
||||
|
||||
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",
|
||||
"srt/mem_cache/storage/hf3fs/hf3fs_utils.cpp",
|
||||
]
|
||||
|
||||
[tool.setuptools.packages.find]
|
||||
exclude = [
|
||||
"assets*",
|
||||
"benchmark*",
|
||||
"docs*",
|
||||
"dist*",
|
||||
"playground*",
|
||||
"scripts*",
|
||||
"tests*",
|
||||
]
|
||||
|
||||
[tool.wheel]
|
||||
exclude = [
|
||||
"assets*",
|
||||
"benchmark*",
|
||||
"docs*",
|
||||
"dist*",
|
||||
"playground*",
|
||||
"scripts*",
|
||||
"tests*",
|
||||
]
|
||||
|
||||
[tool.codespell]
|
||||
ignore-words-list = "ans, als, hel, boostrap, childs, te, vas, hsa, ment"
|
||||
skip = "*.json,*.jsonl,*.patch,*.txt"
|
||||
Reference in New Issue
Block a user