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, 19:45 UTC
[Neuron][CI] update docker run command (#14829)
Signed-off-by: Liangfu Chen <liangfc@amazon.com>
Liangfu Chen committed
Mar 14, 2025 at 18:51 UTC
9f37422779a17d8b2ebde300808166068f4ad4cc
1 file changed
+1
-1
.buildkite/run-neuron-test.sh
+1
-1
@@ -44,7 +44,7 @@ remove_docker_container() {
44
trap remove_docker_container EXIT
45
46
# Run the image
47
-docker run --rm -it --device=/dev/neuron0 --device=/dev/neuron1 --network host \
47
+docker run --rm -it --device=/dev/neuron0 --network bridge \
48
-v "${HF_CACHE}:${HF_MOUNT}" \
49
-e "HF_HOME=${HF_MOUNT}" \
50
-v "${NEURON_COMPILE_CACHE_URL}:${NEURON_COMPILE_CACHE_MOUNT}" \