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 13, 03:15 UTC
[CI] Fix broken pipeline (#28781)
Signed-off-by: Nick Hill <nhill@redhat.com>
Nick Hill committed
Nov 15, 2025 at 08:44 UTC
637f292196237982558936166540ed8d153a75eb
1 file changed
+1
-1
.buildkite/test-pipeline.yaml
+1
-1
@@ -926,7 +926,7 @@ steps:
926
- pytest -v -s tests/kernels/moe/test_ocp_mx_moe.py
927
- pytest -v -s tests/kernels/moe/test_flashinfer.py
928
929
-- label: Blackwell Fusion & Compile Tests # 30 min
929
+- label: Blackwell Fusion and Compile Tests # 30 min
930
timeout_in_minutes: 40
931
working_dir: "/vllm-workspace/"
932
gpu: b200