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
[CI/Build] bump timm dependency (#24189)
Signed-off-by: Daniele Trifirò <dtrifiro@redhat.com> Co-authored-by: Russell Bryant <rbryant@redhat.com>
Daniele committed
Sep 10, 2025 at 15:20 UTC
2f5e5c18de02429263f39fb049d87c7aa61a2b71
1 file changed
+1
-1
docker/Dockerfile
+1
-1
@@ -519,7 +519,7 @@ RUN --mount=type=cache,target=/root/.cache/uv \
519
else \
520
BITSANDBYTES_VERSION="0.46.1"; \
521
fi; \
522
- uv pip install --system accelerate hf_transfer modelscope "bitsandbytes>=${BITSANDBYTES_VERSION}" 'timm==0.9.10' boto3 runai-model-streamer runai-model-streamer[s3]
522
+ uv pip install --system accelerate hf_transfer modelscope "bitsandbytes>=${BITSANDBYTES_VERSION}" 'timm>=1.0.17' boto3 runai-model-streamer runai-model-streamer[s3]
523
524
ENV VLLM_USAGE_SOURCE production-docker-image
525