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 15, 07:15 UTC
[Build][ROCm] Update Dockerfile.rocm (#19296)
Signed-off-by: Alexei V. Ivanov <alexei.ivanov@amd.com>
Alexei-V-Ivanov-AMD committed
Jun 6, 2025 at 18:35 UTC
e010688f50a2e90587a01ada351c5023a10273c2
1 file changed
+2
-1
docker/Dockerfile.rocm
+2
-1
@@ -28,7 +28,8 @@ ARG VLLM_REPO="https://github.com/vllm-project/vllm.git"
28
ARG VLLM_BRANCH="main"
29
ONBUILD RUN git clone ${VLLM_REPO} \
30
&& cd vllm \
31
- && git checkout ${VLLM_BRANCH}
31
+ && git fetch -v --prune -- origin ${VLLM_BRANCH} \
32
+ && git checkout FETCH_HEAD
33
FROM fetch_vllm_${REMOTE_VLLM} AS fetch_vllm
34
35
# -----------------------