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 14, 05:30 UTC
[Bug fix] Dynamically setting the backend variable for genai_perf_tests in the run-nightly-benchmark script (#23375)
Signed-off-by: Naman Lalit <nl2688@nyu.edu>
Naman Lalit committed
Aug 22, 2025 at 08:12 UTC
ebe14621e353217ff16da329c2e76b80ca233b1b
1 file changed
+1
-1
.buildkite/nightly-benchmarks/scripts/run-nightly-benchmarks.sh
+1
-1
@@ -382,7 +382,7 @@ run_genai_perf_tests() {
382
client_command="genai-perf profile \
383
-m $model \
384
--service-kind openai \
385
- --backend vllm \
385
+ --backend "$backend" \
386
--endpoint-type chat \
387
--streaming \
388
--url localhost:$port \