Skip to content

[Perf] Add new npu_fused_infer_attention_score op to improve perfomance in splitfuse cases and resolve long-seq mask problems #9709

[Perf] Add new npu_fused_infer_attention_score op to improve perfomance in splitfuse cases and resolve long-seq mask problems

[Perf] Add new npu_fused_infer_attention_score op to improve perfomance in splitfuse cases and resolve long-seq mask problems #9709

Triggered via pull request September 20, 2025 08:30
Status Success
Total duration 20m 14s
Artifacts 1

image_openeuler.yml

on: pull_request
vllm-ascend image build
9m 34s
vllm-ascend image build
Fit to window
Zoom out
Zoom in

Annotations

1 warning
vllm-ascend image build
The command [sudo apt-get remove -y azure-cli google-chrome-stable firefox powershell mono-devel libgl1-mesa-dri --fix-missing] failed to complete successfully. Proceeding...

Artifacts

Produced during runtime
Name Size Digest
vllm-project~vllm-ascend~C1P5L7.dockerbuild
84.6 KB
sha256:8dc5bcfee06398f8a9db7dd9194d02167a6afdde97d13fc7a5cdd8f4d649198a