aska-0096 746f4ccb99 Load Q through lds, implement xor;

2025-08-04 06:49:01 +00:00

..

__init__.py

[CK_TILE] fmha forward split-kv + combine kernels (#1338)

2024-06-26 17:41:15 +08:00

fmha_batch_prefill.py

[CK_TILE] Low CU utilization optimization for fMHA fwd kernels (#2402)

2025-07-09 22:01:33 +08:00

fmha_bwd.py

update (#2519)

2025-07-17 15:24:19 +08:00

fmha_fwd_appendkv.py

Update FMHA recipe for Pytorch SDPA integration (#2480)

2025-07-10 09:00:23 -07:00

fmha_fwd_decode.py

Load Q through lds, implement xor;

2025-08-04 06:49:01 +00:00

fmha_fwd_splitkv.py

Update FMHA recipe for Pytorch SDPA integration (#2480)

2025-07-10 09:00:23 -07:00

fmha_fwd.py

h_dim256 fmha use async_qr pipeline (#2510)

2025-07-18 09:59:38 +08:00

fmha_pagedkv_prefill.py

ck tile pagedkv prefill (#2405)

2025-07-07 16:16:54 +08:00