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 5, 14:45 UTC
[CI] Add flashinfer.py to attention test source deps (#38792)
Signed-off-by: Stefano Castagnetta <scastagnetta@nvidia.com> Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Stefano Castagnetta committed
Apr 2, 2026 at 21:24 UTC
188defbd0bad837f59dd3fafe1dd779b4bd434cb
1 file changed
+1
.buildkite/test_areas/kernels.yaml
+1
@@ -29,6 +29,7 @@ steps:
29
- vllm/v1/attention
30
# TODO: remove this dependency (https://github.com/vllm-project/vllm/issues/32267)
31
- vllm/model_executor/layers/attention
32
+ - vllm/utils/flashinfer.py
33
- tests/kernels/attention
34
commands:
35
- pytest -v -s kernels/attention --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT