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

expirimental fix

Browse Source
This commit is contained in:
biondizzle
2026-04-15 11:21:32 +00:00
parent e8f51e983f
commit e342c233ff
1 changed files with 2 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
Dockerfile
View File

@@ -9,8 +9,9 @@ RUN apt-get update && apt-get install -y git \
libcurand-dev-13-0 \ libcurand-dev-13-0 \
libcufft-dev-13-0 \ libcufft-dev-13-0 \
libnvjitlink-dev-13-0 && \ libnvjitlink-dev-13-0 && \
git clone --depth 1 https://github.com/LMCache/LMCache.git /tmp/lmcache && \ git clone https://github.com/neuralwatt/LMCache.git /tmp/lmcache && \
cd /tmp/lmcache && \ cd /tmp/lmcache && \
git checkout fix/mla-multi-group-kv-cache && \
CUDA_HOME=/usr/local/cuda \ CUDA_HOME=/usr/local/cuda \
TORCH_CUDA_ARCH_LIST="10.0" \ TORCH_CUDA_ARCH_LIST="10.0" \
pip install --no-cache-dir --no-build-isolation . && \ pip install --no-cache-dir --no-build-isolation . && \