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

Misc fix for min_p_sampling, --cuda-graph-bs (#2761)

Browse Source
This commit is contained in:
Lianmin Zheng
2025-01-07 02:52:53 -08:00
committed by GitHub
parent 6d08ce2aa9
commit bdc1acf6cd
17 changed files with 135 additions and 63 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
python/pyproject.toml
View File

@@ -16,14 +16,20 @@ classifiers = [
dependencies = ["requests", "tqdm", "numpy", "IPython", "setproctitle"]
[project.optional-dependencies]
runtime_common = ["aiohttp", "decord", "fastapi",
runtime_common = [
"aiohttp", "decord", "fastapi",
"hf_transfer", "huggingface_hub", "interegular", "modelscope",
"orjson", "outlines>=0.0.44,<0.1.0",
"packaging", "pillow", "prometheus-client>=0.20.0",
"psutil", "pydantic", "python-multipart",
"pyzmq>=25.1.2", "torchao>=0.7.0", "uvicorn", "uvloop",
"xgrammar>=0.1.6"]
srt = ["sglang[runtime_common]", "torch", "vllm>=0.6.3.post1,<=0.6.4.post1", "cuda-python", "flashinfer==0.1.6", "sgl-kernel>=0.0.2.post11"]
"xgrammar>=0.1.6"
]
srt = [
"sglang[runtime_common]", "cuda-python",
"sgl-kernel>=0.0.2.post11", "torch", "vllm>=0.6.3.post1,<=0.6.4.post1",
"flashinfer==0.1.6"
]
# HIP (Heterogeneous-computing Interface for Portability) for AMD
# => base docker rocm/vllm-dev:20241022, not from public vllm whl