GQA Flash Attention with Attention Mask #19746
Triggered via pull request
November 5, 2023 16:35
Status
Cancelled
Total duration
54m 34s
Artifacts
–
windows.yml
on: pull_request
Windows-CUDA-12
14m 11s
Onnxruntime-TVM
54m 20s
Annotations
3 errors
Windows-CUDA-12
Process completed with exit code 1.
|
Onnxruntime-TVM
Canceling since a higher priority waiting request for 'Windows_CI-aciddelgado/gqa_seqlens_k' exists
|
Onnxruntime-TVM
The operation was canceled.
|