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, 23:45 UTC
[ci] add b200 test placeholder (#21866)
Signed-off-by: simon-mo <simon.mo@hey.com>
Simon Mo committed
Jul 29, 2025 at 17:11 UTC
0d0cc9e15001b18997207fc86af6810500d587d9
1 file changed
+11
.buildkite/test-pipeline.yaml
+11
@@ -643,6 +643,17 @@ steps:
643
- python3 examples/offline_inference/audio_language.py --model-type whisper
644
- python3 examples/offline_inference/vision_language.py --model-type qwen2_5_vl
645
646
+- label: Blackwell Test
647
+ working_dir: "/vllm-workspace/"
648
+ gpu: b200
649
+ # optional: true
650
+ source_file_dependencies:
651
+ - csrc/
652
+ - vllm/
653
+ commands:
654
+ - nvidia-smi
655
+ - python3 examples/offline_inference/basic/chat.py
656
+
657
##### 1 GPU test #####
658
##### multi gpus test #####
659