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, 09:30 UTC
[Bugfix][OpenVINO] fix_dockerfile_openvino (#9552)
ngrozae committed
Oct 22, 2024 at 04:47 UTC
29acd2c34cc542c96dbb584ea089f4b5404e54ef
1 file changed
+4
-4
Dockerfile.openvino
+4
-4
@@ -15,11 +15,11 @@ RUN --mount=type=bind,source=.git,target=.git \
15
if [ "$GIT_REPO_CHECK" != 0 ]; then bash tools/check_repo.sh ; fi
16
17
# install build requirements
18
-RUN PIP_EXTRA_INDEX_URL="https://download.pytorch.org/whl/cpu" python3 -m pip install -r /workspace/vllm/requirements-build.txt
18
+RUN PIP_EXTRA_INDEX_URL="https://download.pytorch.org/whl/cpu" python3 -m pip install -r /workspace/requirements-build.txt
19
# build vLLM with OpenVINO backend
20
-RUN PIP_EXTRA_INDEX_URL="https://download.pytorch.org/whl/cpu" VLLM_TARGET_DEVICE="openvino" python3 -m pip install /workspace/vllm/
20
+RUN PIP_EXTRA_INDEX_URL="https://download.pytorch.org/whl/cpu" VLLM_TARGET_DEVICE="openvino" python3 -m pip install /workspace
21
22
-COPY examples/ /workspace/vllm/examples
23
-COPY benchmarks/ /workspace/vllm/benchmarks
22
+COPY examples/ /workspace/examples
23
+COPY benchmarks/ /workspace/benchmarks
24
25
CMD ["/bin/bash"]