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 10, 02:45 UTC
fixing podman build issue (#32131)
Signed-off-by: Smit Kadvani <smit.kadvani@gmail.com> Co-authored-by: Smit Shaileshbhai Kadvani <kadvani@meta.com> Co-authored-by: Lu Fang <30275821+houseroad@users.noreply.github.com>
smit kadvani committed
Jan 15, 2026 at 09:07 UTC
74e4bb1c5af5d809c48631df44eec13140c6ff4b
1 file changed
+2
docker/Dockerfile.rocm
+2
@@ -39,6 +39,8 @@ ONBUILD COPY ./ vllm/
39
FROM base AS fetch_vllm_1
40
ARG VLLM_REPO="https://github.com/vllm-project/vllm.git"
41
ARG VLLM_BRANCH="main"
42
+ENV VLLM_REPO=${VLLM_REPO}
43
+ENV VLLM_BRANCH=${VLLM_BRANCH}
44
ONBUILD RUN git clone ${VLLM_REPO} \
45
&& cd vllm \
46
&& git fetch -v --prune -- origin ${VLLM_BRANCH} \