[CUDA] Support FP8 (E4M3) KV Cache for Group Query Attention #10427
Triggered via pull request
February 12, 2026 07:16
tianleiwu
Status
Cancelled
Total duration
5m 4s
Artifacts
–
windows_x64_release_xnnpack.yml
on: pull_request
build_x64_release_xnnpack
2m 32s
Annotations
3 errors
|
build_x64_release_xnnpack
Canceling since a higher priority waiting request for windows_x64_release_xnnpack-refs/pull/27321/merge exists
|
|
build_x64_release_xnnpack
The operation was canceled.
|
|
windows_x64_release_xnnpack
Canceling since a higher priority waiting request for windows_x64_release_xnnpack-refs/pull/27321/merge exists
|