A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 16, 03:15 UTC
[OpenVINO] Fixed Docker.openvino build (#11732)
Signed-off-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
Ilya Lavrenov committed
Jan 8, 2025 at 09:08 UTC
f4923cb8bce7d9c3038ad6c597ae1ff3ed90fe93
1 file changed
+1
Dockerfile.openvino
+1
@@ -14,6 +14,7 @@ ARG GIT_REPO_CHECK=0
14
RUN --mount=type=bind,source=.git,target=.git \
15
if [ "$GIT_REPO_CHECK" != 0 ]; then bash tools/check_repo.sh ; fi
16
17
+RUN python3 -m pip install -U pip
18
# install build requirements
19
RUN PIP_EXTRA_INDEX_URL="https://download.pytorch.org/whl/cpu" python3 -m pip install -r /workspace/requirements-build.txt
20
# build vLLM with OpenVINO backend