Skip to content

[CUDA] GroupQueryAttention with XQA and Quantized KV Cache Support #3785

[CUDA] GroupQueryAttention with XQA and Quantized KV Cache Support

[CUDA] GroupQueryAttention with XQA and Quantized KV Cache Support #3785

Triggered via pull request February 9, 2026 18:36
Status Success
Total duration 24m 43s
Artifacts

windows_qnn_x64.yml

on: pull_request
Matrix: build_test_qnn_ep
Fit to window
Zoom out
Zoom in