[Perf] Add new npu_fused_infer_attention_score op to improve perfomance in splitfuse cases and resolve long-seq mask problems #5047
image_310p_openeuler.yml
on: pull_request
vllm-ascend image build
9m 51s
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~DTDE7T.dockerbuild
|
84.6 KB |
sha256:41804c998a4e7f959ecb4545b179bd4d475d1bc41544c922739e889f085dce1c
|
|