[Perf] Add new npu_fused_infer_attention_score op to improve perfomance in splitfuse cases and resolve long-seq mask problems #9582
MengqingCaoimage_ubuntu.yml
on: pull_request
vllm-ascend image build
15m 18s
Annotations
1 error
|
image / Ubuntu
Canceling since a higher priority waiting request for image / Ubuntu-refs/pull/2962/merge exists
|
Artifacts
Produced during runtime
| Name | Size | Digest | |
|---|---|---|---|
|
vllm-project~vllm-ascend~IRQC91.dockerbuild
|
105 KB |
sha256:43be3bec13918dfc2a391603f5a4e9b5a74dd1254b1ba854453dfb02a1a5ea1f
|
|