EngineX-Hygon/sglang
5
0
Fork 0
Code Issues Pull Requests Actions 7 Projects Releases Wiki Activity

Fix install instructions and pyproject.tomls (#11781)

Browse Source
This commit is contained in:
Lianmin Zheng
2025-10-18 01:08:01 -07:00
committed by GitHub
parent 1d726528f7
commit 67e34c56d7
10 changed files with 298 additions and 296 deletions
Download Patch File Download Diff File Expand all files Collapse all files

30
python/pyproject.toml
View File

@@ -13,6 +13,7 @@ classifiers = [
"Programming Language :: Python :: 3",
"License :: OSI Approved :: Apache Software License",
]
dependencies = [
"IPython",
"aiohttp",
@@ -21,6 +22,7 @@ dependencies = [
"build",
"compressed-tensors",
"cuda-python",
"decord2",
"datasets",
"einops",
"fastapi",
@@ -73,7 +75,12 @@ dependencies = [
]
[project.optional-dependencies]
decord = ["decord2"]
tracing = [
"opentelemetry-api",
"opentelemetry-exporter-otlp",
"opentelemetry-exporter-otlp-proto-grpc",
"opentelemetry-sdk",
]
test = [
"accelerate",
"expecttest",
@@ -86,13 +93,10 @@ test = [
"sentence_transformers",
"tabulate",
]
tracing = [
"opentelemetry-api",
"opentelemetry-exporter-otlp",
"opentelemetry-exporter-otlp-proto-grpc",
"opentelemetry-sdk",
]
all = ["sglang[test]", "sglang[decord]"]
all = []
dev = ["sglang[test]"]
# Temporary tags
cu130 = [
"torch==2.9.0",
"torchaudio==2.9.0",
@@ -104,13 +108,9 @@ cu130_all = [
"sglang[cu130]"
]
# The following will be deprecated in 2 weeks
dev = ["sglang[test]", "sglang[decord]"]
all_aarch64 = ["sglang[test]"]
blackwell = ["sglang[test]", "sglang[decord]"]
blackwell_aarch64 = ["sglang[test]"]
# To be deprecated in 2 weeks
blackwell = ["sglang[dev]"]
blackwell_aarch64 = ["sglang[dev]"]
[project.urls]
"Homepage" = "https://github.com/sgl-project/sglang"

167
python/pyproject_cpu.toml
View File

@@ -5,85 +5,88 @@ build-backend = "setuptools.build_meta"
[project]
name = "sglang"
version = "0.5.3rc0"
version = "0.5.3.post3"
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",
"Programming Language :: Python :: 3",
"License :: OSI Approved :: Apache Software License",
]
dependencies = [
"aiohttp",
"anthropic>=0.20.0",
"blobfile==3.0.0",
"build",
"compressed-tensors",
"datasets",
"decord",
"einops",
"fastapi",
"hf_transfer",
"huggingface_hub",
"intel-openmp",
"interegular",
"IPython",
"llguidance>=0.7.11,<0.8.0",
"modelscope",
"msgspec",
"ninja",
"numpy",
"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",
"python-multipart",
"pyzmq>=25.1.2",
"requests",
"scipy",
"sentencepiece",
"setproctitle",
"soundfile==0.13.1",
"tiktoken",
"timm==1.0.16",
"torchao==0.9.0",
"tqdm",
"transformers==4.57.1",
"uvicorn",
"uvloop",
"xgrammar==0.1.25",
"IPython",
"aiohttp",
"anthropic>=0.20.0",
"blobfile==3.0.0",
"build",
"compressed-tensors",
"datasets",
"decord",
"einops",
"fastapi",
"hf_transfer",
"huggingface_hub",
"intel-openmp",
"interegular",
"llguidance>=0.7.11,<0.8.0",
"modelscope",
"msgspec",
"ninja",
"numpy",
"openai-harmony==0.0.4",
"openai==1.99.1",
"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",
"transformers==4.57.1",
"uvicorn",
"uvloop",
"xgrammar==0.1.25",
"grpcio==1.75.1", # keep it align with compile_proto.py
"grpcio-tools==1.75.1", # keep it align with compile_proto.py
"grpcio-reflection==1.75.1", # required by srt/entrypoints/grpc_server.py
]
[project.optional-dependencies]
tracing = [
"opentelemetry-sdk",
"opentelemetry-api",
"opentelemetry-exporter-otlp",
"opentelemetry-exporter-otlp-proto-grpc",
"opentelemetry-sdk",
"opentelemetry-api",
"opentelemetry-exporter-otlp",
"opentelemetry-exporter-otlp-proto-grpc",
]
test = [
"accelerate",
"expecttest",
"jsonlines",
"matplotlib",
"pandas",
"peft",
"sentence_transformers",
"pytest",
"tabulate",
"accelerate",
"expecttest",
"jsonlines",
"matplotlib",
"pandas",
"peft",
"pytest",
"sentence_transformers",
"tabulate",
]
dev = ["sglang", "sglang[test]"]
all = []
dev = ["sglang[test]"]
[project.urls]
"Homepage" = "https://github.com/sgl-project/sglang"
@@ -91,31 +94,33 @@ dev = ["sglang", "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",
"srt/speculative/cpp_ngram/*.cpp",
"srt/speculative/cpp_ngram/*.h",
]
[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]

184
python/pyproject_other.toml
View File

@@ -10,76 +10,77 @@ 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"]
[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==4.57.1",
"uvicorn",
"uvloop",
"xgrammar==0.1.25",
"IPython",
"aiohttp",
"anthropic>=0.20.0",
"blobfile==3.0.0",
"build",
"compressed-tensors",
"decord2",
"datasets",
"einops",
"fastapi",
"hf_transfer",
"huggingface_hub",
"interegular",
"llguidance>=0.7.11,<0.8.0",
"modelscope",
"msgspec",
"ninja",
"numpy",
"openai-harmony==0.0.4",
"openai==1.99.1",
"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",
"transformers==4.57.1",
"uvicorn",
"uvloop",
"xgrammar==0.1.25",
"grpcio==1.75.1", # keep it align with compile_proto.py
"grpcio-tools==1.75.1", # keep it align with compile_proto.py
"grpcio-reflection==1.75.1", # required by srt/entrypoints/grpc_server.py
]
tracing = [
"opentelemetry-sdk",
"opentelemetry-api",
"opentelemetry-exporter-otlp",
"opentelemetry-exporter-otlp-proto-grpc",
]
srt = [
"sglang[runtime_common]",
"sgl-kernel==0.3.15",
"torch==2.8.0",
"torchaudio==2.8.0",
"torchvision",
"cuda-python",
"flashinfer_python==0.4.0",
"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==3.7.0",
"sglang[runtime_common]",
"torch",
"petit_kernel==0.0.2",
"wave-lang==3.7.0",
]
# https://docs.sglang.ai/platforms/ascend_npu.html
@@ -89,29 +90,24 @@ srt_npu = ["sglang[runtime_common]"]
# 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==0.0.9rc1"]
decord = ["decord"]
test = [
"accelerate",
"expecttest",
"jsonlines",
"matplotlib",
"pandas",
"peft",
"sentence_transformers",
"pytest",
"tabulate",
"accelerate",
"expecttest",
"gguf",
"jsonlines",
"matplotlib",
"pandas",
"peft",
"pytest",
"sentence_transformers",
"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_hpu = ["sglang[srt_hpu]", "sglang[openai]", "sglang[anthropic]", "sglang[decord]"]
all_npu = ["sglang[srt_npu]", "sglang[openai]", "sglang[anthropic]", "sglang[decord]"]
all_hip = ["sglang[srt_hip]"]
all_npu = ["sglang[srt_npu]"]
all_hpu = ["sglang[srt_hpu]"]
dev = ["sglang[all]", "sglang[test]"]
dev_hip = ["sglang[all_hip]", "sglang[test]"]
dev_npu = ["sglang[all_npu]", "sglang[test]"]
dev_hpu = ["sglang[all_hpu]", "sglang[test]"]
[project.urls]
@@ -120,31 +116,33 @@ dev_hpu = ["sglang[all_hpu]", "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",
"srt/speculative/cpp_ngram/*.cpp",
"srt/speculative/cpp_ngram/*.h",
]
[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]

165
python/pyproject_xpu.toml
View File

@@ -6,84 +6,87 @@ build-backend = "setuptools.build_meta"
[project]
name = "sglang"
version = "0.5.3rc0"
version = "0.5.3.post3"
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",
"Programming Language :: Python :: 3",
"License :: OSI Approved :: Apache Software License",
]
dependencies = [
"aiohttp",
"anthropic>=0.20.0",
"blobfile==3.0.0",
"build",
"compressed-tensors",
"datasets",
"decord",
"einops",
"fastapi",
"hf_transfer",
"huggingface_hub",
"interegular",
"IPython",
"llguidance>=0.7.11,<0.8.0",
"modelscope",
"msgspec",
"ninja",
"numpy",
"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",
"python-multipart",
"pyzmq>=25.1.2",
"requests",
"scipy",
"sentencepiece",
"setproctitle",
"soundfile==0.13.1",
"tiktoken",
"timm==1.0.16",
"torchao==0.9.0",
"tqdm",
"transformers==4.57.1",
"uvicorn",
"uvloop",
"xgrammar==0.1.25",
"IPython",
"aiohttp",
"anthropic>=0.20.0",
"blobfile==3.0.0",
"build",
"compressed-tensors",
"datasets",
"decord",
"einops",
"fastapi",
"hf_transfer",
"huggingface_hub",
"interegular",
"llguidance>=0.7.11,<0.8.0",
"modelscope",
"msgspec",
"ninja",
"numpy",
"openai-harmony==0.0.4",
"openai==1.99.1",
"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",
"transformers==4.57.1",
"uvicorn",
"uvloop",
"xgrammar==0.1.25",
"grpcio==1.75.1", # keep it align with compile_proto.py
"grpcio-tools==1.75.1", # keep it align with compile_proto.py
"grpcio-reflection==1.75.1", # required by srt/entrypoints/grpc_server.py
]
[project.optional-dependencies]
tracing = [
"opentelemetry-sdk",
"opentelemetry-api",
"opentelemetry-exporter-otlp",
"opentelemetry-exporter-otlp-proto-grpc",
"opentelemetry-sdk",
"opentelemetry-api",
"opentelemetry-exporter-otlp",
"opentelemetry-exporter-otlp-proto-grpc",
]
test = [
"accelerate",
"expecttest",
"jsonlines",
"matplotlib",
"pandas",
"peft",
"sentence_transformers",
"pytest",
"tabulate",
"accelerate",
"expecttest",
"jsonlines",
"matplotlib",
"pandas",
"peft",
"pytest",
"sentence_transformers",
"tabulate",
]
dev = ["sglang", "sglang[test]"]
all = []
dev = ["sglang[test]"]
[project.urls]
"Homepage" = "https://github.com/sgl-project/sglang"
@@ -91,31 +94,33 @@ dev = ["sglang", "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",
"srt/speculative/cpp_ngram/*.cpp",
"srt/speculative/cpp_ngram/*.h",
]
[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]

2
python/sglang/srt/model_executor/model_runner.py
View File

@@ -623,7 +623,7 @@ class ModelRunner:
server_args.disable_chunked_prefix_cache = True
if not server_args.disable_chunked_prefix_cache:
logger.info("Chunked prefix cache is turned on.")
log_info_on_rank0(logger, "Chunked prefix cache is turned on.")
if server_args.attention_backend == "aiter":
if self.model_config.context_len > 8192:

7
python/sglang/srt/server_args.py
View File

@@ -253,7 +253,6 @@ class ServerArgs:
log_requests: bool = False
log_requests_level: int = 2
crash_dump_folder: Optional[str] = None
crash_on_nan: bool = False
show_time_cost: bool = False
enable_metrics: bool = False
enable_metrics_for_all_schedulers: bool = False
@@ -1899,12 +1898,6 @@ class ServerArgs:
default=ServerArgs.crash_dump_folder,
help="Folder path to dump requests from the last 5 min before a crash (if any). If not specified, crash dumping is disabled.",
)
parser.add_argument(
"--crash-on-nan",
type=str,
default=ServerArgs.crash_on_nan,
help="Crash the server on nan logprobs.",
)
parser.add_argument(
"--show-time-cost",
action="store_true",