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, 18:30 UTC
[Build/CI] Fix env var typo (#15305)
Signed-off-by: Russell Bryant <rbryant@redhat.com>
Russell Bryant committed
Mar 21, 2025 at 18:28 UTC
790b79750b596043036b9fcbee885827fdd2ef3d
1 file changed
+1
-1
.buildkite/nightly-benchmarks/scripts/run-performance-benchmarks.sh
+1
-1
@@ -361,7 +361,7 @@ main() {
361
# get the current IP address, required by benchmark_serving.py
362
export VLLM_HOST_IP=$(hostname -I | awk '{print $1}')
363
# turn of the reporting of the status of each request, to clean up the terminal output
364
- export VLLM_LOG_LEVEL="WARNING"
364
+ export VLLM_LOGGING_LEVEL="WARNING"
365
366
# prepare for benchmarking
367
cd benchmarks || exit 1