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 5, 07:15 UTC
[CI/Build] Fix sentence-transformers version in CPU test (#39557)
Signed-off-by: jiang1.li <jiang1.li@intel.com>
Li, Jiang committed
Apr 11, 2026 at 15:04 UTC
eb92ba740a63c2ae590ccfb16f07b490d261d30a
1 file changed
+2
docker/Dockerfile.cpu
+2
@@ -143,6 +143,8 @@ RUN \
143
sed -i 's/^torch==.*/torch==2.11.0/g' requirements/test/cpu.in && \
144
sed -i 's/torchaudio.*/torchaudio/g' requirements/test/cpu.in && \
145
sed -i 's/torchvision.*/torchvision/g' requirements/test/cpu.in && \
146
+ # Related issue: https://github.com/vllm-project/vllm/pull/38800#issuecomment-4228314305
147
+ sed -i 's/^sentence-transformers.*/sentence-transformers==5.3.0/g' requirements/test/cpu.in && \
148
uv pip compile requirements/test/cpu.in -o requirements/test/cpu.txt --index-strategy unsafe-best-match --torch-backend cpu
149
150
RUN --mount=type=cache,target=/root/.cache/uv \