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

[AMD] Fix rocm sgl-kernel missing modules error (#4311)

Browse Source 
Co-authored-by: yiakwy-xpu-ml-framework-team <leiwang2@amd.com>
This commit is contained in:
yigex
2025-03-12 01:35:28 +08:00
committed by GitHub
parent 00f42707ea
commit 690e1f2371
3 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
python/pyproject.toml
View File

@@ -54,7 +54,7 @@ srt = [
# HIP (Heterogeneous-computing Interface for Portability) for AMD
# => base docker rocm/vllm-dev:20250114, not from public vllm whl
srt_hip = ["sglang[runtime_common]", "sgl-kernel==0.0.3.post6", "torch", "vllm==0.6.7.dev2", "outlines==0.1.11"]
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