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, 06:00 UTC
[BugFix] Fix docker build cpu-dev image error (#19394)
Signed-off-by: niu_he <carlton2tang@gmail.com>
niu_he committed
Jun 11, 2025 at 11:56 UTC
a45b979d9fe4e700a81256ad314a9d5fd65a2829
1 file changed
+4
docker/Dockerfile.cpu
+4
@@ -98,6 +98,10 @@ RUN --mount=type=cache,target=/root/.cache/uv \
98
VLLM_TARGET_DEVICE=cpu python3 setup.py develop
99
100
RUN --mount=type=cache,target=/root/.cache/uv \
101
+ --mount=type=bind,src=requirements/test.in,target=requirements/test.in \
102
+ cp requirements/test.in requirements/test-cpu.in && \
103
+ sed -i '/mamba_ssm/d' requirements/test-cpu.in && \
104
+ uv pip compile requirements/test-cpu.in -o requirements/test.txt && \
105
uv pip install -r requirements/dev.txt && \
106
pre-commit install --hook-type pre-commit --hook-type commit-msg
107