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, 15:45 UTC
[CI/Build] fix Dockerfile.cpu on podman (#8540)
Daniele committed
Sep 18, 2024 at 04:49 UTC
95965d31b6ac2c9557816a6ffabe4a3117a5ccb2
1 file changed
+2
Dockerfile.cpu
+2
@@ -24,6 +24,8 @@ RUN echo 'ulimit -c 0' >> ~/.bashrc
24
25
RUN pip install https://intel-extension-for-pytorch.s3.amazonaws.com/ipex_dev/cpu/intel_extension_for_pytorch-2.4.0%2Bgitfbaa4bc-cp310-cp310-linux_x86_64.whl
26
27
+WORKDIR /workspace
28
+
29
ENV PIP_EXTRA_INDEX_URL=https://download.pytorch.org/whl/cpu
30
RUN --mount=type=cache,target=/root/.cache/pip \
31
--mount=type=bind,src=requirements-build.txt,target=requirements-build.txt \