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 14, 05:30 UTC
Update Dockerfile and install runai-model-streamer[gcs] package (#26464)
Signed-off-by: Peter Schuurman <psch@google.com>
pwschuurman committed
Oct 8, 2025 at 23:48 UTC
0d7c3cb51dcd0b90c203b7d36f15442a45b7e4b5
1 file changed
+1
-1
docker/Dockerfile
+1
-1
@@ -542,7 +542,7 @@ RUN --mount=type=cache,target=/root/.cache/uv \
542
else \
543
BITSANDBYTES_VERSION="0.46.1"; \
544
fi; \
545
- uv pip install --system accelerate hf_transfer modelscope "bitsandbytes>=${BITSANDBYTES_VERSION}" 'timm>=1.0.17' 'runai-model-streamer[s3]>=0.14.0'
545
+ uv pip install --system accelerate hf_transfer modelscope "bitsandbytes>=${BITSANDBYTES_VERSION}" 'timm>=1.0.17' 'runai-model-streamer[s3,gcs]>=0.14.0'
546
547
ENV VLLM_USAGE_SOURCE production-docker-image
548