Po Yen Chen ad9863fe05 [CK_TILE] Low CU utilization optimization for fMHA fwd kernels (#2402) ...

* Wrap tile size mapping as class method

* Warp pipeline generating as class method

* Add constraint as kernel dispatching criteria

* Support mutltiple tile size for a (hdim, hdim_v) combination

* Use smaller tile size if CU utilization is low

* Use integar as the key of the tile size map

* Fix type error

* Simply override parent class method return value

* Add attribute to eliminate warnging

* Allow using environment variables to turn on/off custom factory

* Unify param naming style

* Add missing HIP runtime include directive

* Fix os.environ.get() usage

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

..

__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

[CK TILE] Fix FA build filter (#2369)

2025-07-08 10:42:07 +08:00

fmha_fwd_appendkv.py

Only generate specific hdim (#2120)

2025-04-24 18:52:58 +08:00

fmha_fwd_splitkv.py

[CK_TILE] FMHA Support hdim_v to as a Multiple of 32 (#2114)

2025-06-24 01:33:31 +08:00

fmha_fwd.py

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

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

fmha_pagedkv_prefill.py

ck tile pagedkv prefill (#2405)

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