Skip to content

[CUDA] Support head_sink in flash attention for GQA#25432

Merged
tianleiwu merged 4 commits intomainfrom
tlwu/gqa_head_sink_cuda
Jul 17, 2025
Merged

[CUDA] Support head_sink in flash attention for GQA#25432
tianleiwu merged 4 commits intomainfrom
tlwu/gqa_head_sink_cuda

Commits

Commits on Jul 17, 2025