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
Disable failing GPT-OSS Eval (Blackwell) for now (#25107)
Signed-off-by: mgoin <mgoin64@gmail.com>
Michael Goin committed
Sep 17, 2025 at 18:36 UTC
9f882d879198200104fed7e166d40dd11039d217
1 file changed
+1
-1
.buildkite/test-pipeline.yaml
+1
-1
@@ -812,7 +812,7 @@ steps:
812
timeout_in_minutes: 60
813
working_dir: "/vllm-workspace/"
814
gpu: b200
815
- # optional: true
815
+ optional: true # disable while debugging
816
source_file_dependencies:
817
- tests/evals/gpt_oss
818
- vllm/model_executor/models/gpt_oss.py