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 12, 02:15 UTC
[Misc] Add docker build env for Ascend NPU (#30015)
Signed-off-by: wangli <wangli858794774@gmail.com>
Li Wang committed
Dec 4, 2025 at 11:53 UTC
5f91cdda75b24a3d9cdda8c82897db07b288b5c9
1 file changed
+1
.buildkite/scripts/hardware_ci/run-npu-test.sh
+1
@@ -74,6 +74,7 @@ FROM ${BASE_IMAGE_NAME}
74
75
# Define environments
76
ENV DEBIAN_FRONTEND=noninteractive
77
+ENV SOC_VERSION="ascend910b1"
78
79
RUN pip config set global.index-url http://cache-service-vllm.nginx-pypi-cache.svc.cluster.local:${PYPI_CACHE_PORT}/pypi/simple && \
80
pip config set global.trusted-host cache-service-vllm.nginx-pypi-cache.svc.cluster.local && \