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 8, 02:30 UTC
[CI][Bugfix] Fix multinode test script (#34820)
Signed-off-by: ilmarkov <markovilya197@gmail.com>
Ilya Markov committed
Feb 18, 2026 at 17:45 UTC
6b3166a7c7b4274317ac1cb18a55d56f3f94077f
1 file changed
+1
-1
.buildkite/scripts/run-multi-node-test.sh
+1
-1
@@ -67,7 +67,7 @@ start_nodes() {
67
# 3. map the huggingface cache directory to the container
68
# 3. assign ip addresses to the containers (head node: 192.168.10.10, worker nodes:
69
# starting from 192.168.10.11)
70
- docker run -d "$GPU_DEVICES" --shm-size=10.24gb -e HF_TOKEN \
70
+ docker run -d $GPU_DEVICES --shm-size=10.24gb -e HF_TOKEN \
71
-v ~/.cache/huggingface:/root/.cache/huggingface --name "node$node" \
72
--network docker-net --ip 192.168.10.$((10 + $node)) --rm "$DOCKER_IMAGE" \
73
/bin/bash -c "tail -f /dev/null"