Skip to content
Back to pull request #25594

[webgpu] Apply Flash Attention if sliding window exceeds KV cache length #5076

Sign in to view logs

[webgpu] Apply Flash Attention if sliding window exceeds KV cache length

[webgpu] Apply Flash Attention if sliding window exceeds KV cache length #5076

Re-run triggered August 1, 2025 15:02
@guschmueguschmue
#25594
daijh:supports-sliding-window-for-flash-attention
Status Success
Total duration 2h 17m 15s
Artifacts 1

windows_tensorrt.yml

on: pull_request
Windows GPU TensorRT CI Pipeline
41m 16s
Windows GPU TensorRT CI Pipeline
Windows GPU TensorRT CI Pipeline Test Job
1h 3m
Windows GPU TensorRT CI Pipeline Test Job
Fit to window
Zoom out
Zoom in

Artifacts

Produced during runtime
Name Size Digest
build-artifacts Expired
1.71 GB
sha256:c0bb5734ee76d9966d9fe6c829862bb8ae383a374fa1731138c2c8aa65f60454