"vscode:/vscode.git/clone" did not exist on "fa5610673196a22a59cf439ed8140632d2dc072d"
pyproject_other.toml 3.28 KB
Newer Older
1
2
3
4
5
6
[build-system]
requires = ["setuptools>=61.0", "wheel"]
build-backend = "setuptools.build_meta"

[project]
name = "sglang"
7
version = "0.5.5"
8
9
10
11
12
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 = [
13
14
  "Programming Language :: Python :: 3",
  "License :: OSI Approved :: Apache Software License",
15
16
17
18
19
]
dependencies = ["aiohttp", "requests", "tqdm", "numpy", "IPython", "setproctitle"]

[project.optional-dependencies]
runtime_common = [
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
  "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
68
69
70
]

tracing = [
71
72
73
74
  "opentelemetry-sdk",
  "opentelemetry-api",
  "opentelemetry-exporter-otlp",
  "opentelemetry-exporter-otlp-proto-grpc",
75
76
77
78
79
]

# HIP (Heterogeneous-computing Interface for Portability) for AMD
# => base docker rocm/vllm-dev:20250114, not from public vllm whl
srt_hip = [
80
81
82
  "sglang[runtime_common]",
  "torch",
  "petit_kernel==0.0.2",
83
  "wave-lang==3.8.0",
84
85
86
87
88
89
90
91
92
93
]

# https://docs.sglang.ai/platforms/ascend_npu.html
srt_npu = ["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]"]

test = [
94
95
96
97
98
99
100
101
102
103
  "accelerate",
  "expecttest",
  "gguf",
  "jsonlines",
  "matplotlib",
  "pandas",
  "peft",
  "pytest",
  "sentence_transformers",
  "tabulate",
104
]
105
106
107
all_hip = ["sglang[srt_hip]"]
all_npu = ["sglang[srt_npu]"]
all_hpu = ["sglang[srt_hpu]"]
108
109

dev_hip = ["sglang[all_hip]", "sglang[test]"]
110
dev_npu = ["sglang[all_npu]", "sglang[test]"]
111
112
113
114
115
116
117
118
dev_hpu = ["sglang[all_hpu]", "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" = [
119
120
121
122
123
  "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",
124
125
126
127
]

[tool.setuptools.packages.find]
exclude = [
128
129
130
131
132
133
134
  "assets*",
  "benchmark*",
  "docs*",
  "dist*",
  "playground*",
  "scripts*",
  "tests*",
135
136
137
138
]

[tool.wheel]
exclude = [
139
140
141
142
143
144
145
  "assets*",
  "benchmark*",
  "docs*",
  "dist*",
  "playground*",
  "scripts*",
  "tests*",
146
147
148
149
150
]

[tool.codespell]
ignore-words-list = "ans, als, hel, boostrap, childs, te, vas, hsa, ment"
skip = "*.json,*.jsonl,*.patch,*.txt"