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, 04:45 UTC
[CI][Neuron] Fail and exit on first error (#19622)
Signed-off-by: Elaine Zhao <elaineyz@amazon.com> Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Elaine Zhao committed
Jun 19, 2025 at 21:27 UTC
b6bad3d1865238faf304be5963f1a523304e1f43
1 file changed
+2
-1
.buildkite/scripts/hardware_ci/run-neuron-test.sh
+2
-1
@@ -54,10 +54,11 @@ docker run --rm -it --device=/dev/neuron0 --network bridge \
54
--name "${container_name}" \
55
${image_name} \
56
/bin/bash -c "
57
+ set -e; # Exit on first error
58
python3 /workspace/vllm/examples/offline_inference/neuron.py;
59
python3 -m pytest /workspace/vllm/tests/neuron/1_core/ -v --capture=tee-sys;
60
for f in /workspace/vllm/tests/neuron/2_core/*.py; do
60
- echo 'Running test file: '$f;
61
+ echo \"Running test file: \$f\";
62
python3 -m pytest \$f -v --capture=tee-sys;
63
done
64
"
\ No newline at end of file