[XPU] Enable qwen3.5 on XPU (#21668)

Co-authored-by: Ma Mingfei <mingfei.ma@intel.com>
2026-05-18 14:59:19 +08:00
parent 1f9eda4ea1
commit 8d5ed330cc
14 changed files with 757 additions and 13 deletions
@@ -67,6 +67,8 @@ cp pyproject_xpu.toml pyproject.toml
 # Install SGLang dependent libs, and build SGLang main package
 pip install --upgrade pip setuptools
 pip install -v . --extra-index-url https://download.pytorch.org/whl/xpu
+# Using this version of triton-xpu to avoid a bug in the version shipped with torch 2.11.0+xpu
+pip install triton-xpu --index-url https://download.pytorch.org/whl/test/xpu --force-reinstall # index will change after torch 2.12 release
 ```

 ### Install Using Docker