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 11, 03:45 UTC
ci: add nvidia-smi warmup before Prime-RL integration test (#31093)
Signed-off-by: AmeenP <ameenp360@gmail.com>
Ameen Patel committed
Dec 21, 2025 at 07:43 UTC
93cabc417cf88210f16ebf4b3c20b9adbe9ed83a
1 file changed
+1
.buildkite/test-pipeline.yaml
+1
@@ -1359,6 +1359,7 @@ steps:
1359
- vllm/
1360
- .buildkite/scripts/run-prime-rl-test.sh
1361
commands:
1362
+ - nvidia-smi
1363
- bash .buildkite/scripts/run-prime-rl-test.sh
1364
1365
- label: DeepSeek V2-Lite Accuracy