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, 14:45 UTC
[CI/Build] Add audio deps in Dockerfile.cpu (#38876)
Signed-off-by: jiang1.li <jiang1.li@intel.com>
Li, Jiang committed
Apr 3, 2026 at 13:05 UTC
21d7ecc5b0f5002bb08d450facb5a7338dc6adfa
1 file changed
+2
-1
docker/Dockerfile.cpu
+2
-1
@@ -203,7 +203,8 @@ WORKDIR /vllm-workspace
203
RUN --mount=type=cache,target=/root/.cache/uv \
204
--mount=type=cache,target=/root/.cache/ccache \
205
--mount=type=bind,from=vllm-build,src=/vllm-workspace/dist,target=dist \
206
- uv pip install dist/*.whl
206
+ uv pip install dist/*.whl && \
207
+ uv pip install "vllm[audio]"
208
209
# Add labels to document build configuration
210
LABEL org.opencontainers.image.title="vLLM CPU"