root cd7ba6e2e8 Add unified attention (42_unified_attention) ...

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

2026-04-01 16:39:15 +00:00

..

ck

[rocm-libraries] ROCm/rocm-libraries#6022 (commit 54b284a)

2026-03-31 15:19:43 +00:00

ck_tile

Add unified attention (42_unified_attention)

2026-04-01 16:39:15 +00:00

rapidjson

Update pre-commit to fixed versions, run remod for ck_tile (#2895)

2025-10-16 15:29:17 -07:00