[Feature] Reduce host memory usage for attention mask generation #12877
Triggered via pull request
September 20, 2025 00:09
jianzs
Status
Failure
Total duration
36m 30s
Artifacts
–
vllm_ascend_test.yaml
on: pull_request
Matrix: singlecard e2e test - light
Matrix: unit test
Matrix: multicard e2e test - light
Annotations
1 error
|
unit test (v0.10.2)
Process completed with exit code 1.
|