biondizzle/vllm-glm
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix git

Browse Source
This commit is contained in:
biondizzle
2026-04-15 07:27:01 +00:00
parent 64784741de
commit 2cfd5f5027
1 changed files with 6 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
Dockerfile
View File

@@ -11,7 +11,11 @@ COPY vllm_patches/hf.py /usr/local/lib/python3.12/dist-packages/vllm/renderers/h
# Install LMCache for KV cache offloading / sharing across nodes
# Build from source to match CUDA 13 (pip wheel is CUDA 12)
RUN git clone --depth 1 https://github.com/LMCache/LMCache.git /tmp/lmcache && \
RUN apt-get update && apt-get install -y --no-install-recommends git && \
git clone --depth 1 https://github.com/LMCache/LMCache.git /tmp/lmcache && \
cd /tmp/lmcache && \
pip install --no-cache-dir --no-build-isolation -e . && \
rm -rf /tmp/lmcache
rm -rf /tmp/lmcache && \
apt-get remove -y git && \
apt-get autoremove -y && \
rm -rf /var/lib/apt/lists/*