[XPU] Add XPU device support for LMCache radix cache integration (#23534)

Co-authored-by: Christopher Manteuffel <christopher.manteuffel@intel.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: Ma Mingfei <mingfei.ma@intel.com>
This commit is contained in:
Libin Tang
2026-07-24 08:41:01 +08:00
committed by GitHub
co-authored by Christopher Manteuffel Claude Opus 4.8 Ma Mingfei
parent 2f823a2eee
commit 1e10ec93b3
6 changed files with 633 additions and 16 deletions
+2 -2
View File
@@ -103,7 +103,7 @@ 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
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 uninstall -y flashinfer-python sgl-kernel sglang
docker exec ci_sglang_xpu cp /sglang-checkout/python/pyproject_xpu.toml /sglang-checkout/python/pyproject.toml
docker exec -w /sglang-checkout/python ci_sglang_xpu /opt/venv/bin/python3 -m pip install --no-cache-dir . --extra-index-url https://download.pytorch.org/whl/xpu
@@ -179,7 +179,7 @@ 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
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 uninstall -y flashinfer-python sgl-kernel sglang
docker exec ci_sglang_xpu cp /sglang-checkout/python/pyproject_xpu.toml /sglang-checkout/python/pyproject.toml
docker exec -w /sglang-checkout/python ci_sglang_xpu /opt/venv/bin/python3 -m pip install --no-cache-dir . --extra-index-url https://download.pytorch.org/whl/xpu