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 10, 12:45 UTC
[CI][BugFix][AMD] Actually skip tests marked @pytest.mark.skip_v1 (#31873)
Signed-off-by: Randall Smith <ransmith@amd.com> Co-authored-by: Randall Smith <ransmith@amd.com>
rasmith committed
Jan 7, 2026 at 23:06 UTC
f1b1bea5c36d48561e7ef4cf4d76ffb2529e3212
1 file changed
+1
-2
.buildkite/test-amd.yaml
+1
-2
@@ -517,8 +517,7 @@ steps:
517
- tests/samplers
518
- tests/conftest.py
519
commands:
520
- - pytest -v -s samplers
521
- - VLLM_USE_FLASHINFER_SAMPLER=1 pytest -v -s samplers
520
+ - pytest -v -s -m 'not skip_v1' samplers
521
522
- label: LoRA Test %N # 20min each
523
timeout_in_minutes: 30