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
Fix the path to the testing script. (#20082)
Signed-off-by: Qiliang Cui <derrhein@gmail.com>
QiliangCui committed
Jun 25, 2025 at 13:48 UTC
4e0db57fff89cc968794650c9b9caf4ccc51b399
1 file changed
+1
-1
.buildkite/scripts/tpu/docker_run_bm.sh
+1
-1
@@ -68,7 +68,7 @@ docker run \
68
69
echo "run script..."
70
echo
71
-docker exec "$CONTAINER_NAME" /bin/bash -c ".buildkite/scripts/hardware_ci/run_bm.sh"
71
+docker exec "$CONTAINER_NAME" /bin/bash -c ".buildkite/scripts/tpu/run_bm.sh"
72
73
echo "copy result back..."
74
VLLM_LOG="$LOG_ROOT/$TEST_NAME"_vllm_log.txt