minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity

[Intel][XPU][LoRA] Enable LoRA on Intel XPU (#30345)

Browse Source
This commit is contained in:
Anupa Sajikumar
2026-09-08 12:46:41 +08:00
committed by GitHub
parent 80e9a4ec74
commit 91a45ea37e
19 changed files with 1262 additions and 78 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.github/workflows/pr-test-xpu.yml
+2 -2
View File
@@ -110,7 +110,7 @@ jobs:
timeout-minutes: 60
run: |
docker exec ci_sglang_xpu /opt/venv/bin/python3 -m pip install --upgrade pip
docker exec ci_sglang_xpu /opt/venv/bin/python3 -m pip install pytest expecttest ray huggingface_hub tabulate "lmcache>=0.3.9"
docker exec ci_sglang_xpu /opt/venv/bin/python3 -m pip install pytest expecttest ray huggingface_hub tabulate "lmcache>=0.3.9" accelerate
docker exec ci_sglang_xpu /opt/venv/bin/python3 -m pip uninstall -y flashinfer-python sgl-kernel sglang
docker exec ci_sglang_xpu cp /sglang-checkout/python/pyproject_xpu.toml /sglang-checkout/python/pyproject.toml
# Fetch tags so setuptools_scm resolves a real version instead of
@@ -202,7 +202,7 @@ jobs:
timeout-minutes: 60
run: |
docker exec ci_sglang_xpu /opt/venv/bin/python3 -m pip install --upgrade pip
docker exec ci_sglang_xpu /opt/venv/bin/python3 -m pip install pytest expecttest ray huggingface_hub tabulate "lmcache>=0.3.9"
docker exec ci_sglang_xpu /opt/venv/bin/python3 -m pip install pytest expecttest ray huggingface_hub tabulate "lmcache>=0.3.9" accelerate
docker exec ci_sglang_xpu /opt/venv/bin/python3 -m pip uninstall -y flashinfer-python sgl-kernel sglang
docker exec ci_sglang_xpu cp /sglang-checkout/python/pyproject_xpu.toml /sglang-checkout/python/pyproject.toml
# Fetch tags so setuptools_scm resolves a real version instead of