Skip to content
test

[Perf] Add new npu_fused_infer_attention_score op to improve perfomance in splitfuse cases and resolve long-seq mask problems #12888

Sign in to view logs

[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 #12888

Run time

Learn about OS pricing on GitHub Actions
Job Run time
changes
5s
lint / pre-commit
6m 36s
singlecard e2e test - light (linux-aarch64-a2-1, v0.10.2)
14m 43s
unit test (v0.10.2)
9m 10s
multicard e2e test - light (linux-aarch64-a2-2, v0.10.2)
12m 2s
42m 36s