mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-14 18:17:44 +00:00
Squashed from aghamari/unified-attention-decode-opt branch. CK tile paged-KV attention kernel optimized for decode with 4-tier dispatch (tiny/small/medium/large), 16x16 MFMA, 2D decode grid, head-group merging. Supports hdim=64 GQA-8 and hdim=128 MHA with block_size=32. Made-with: Cursor