mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-02 12:41:26 +00:00

Files

Po Yen Chen 05292b3604 [CK_TILE][FMHA] Integrate FAv2 & FAv3 (WIP) in the single fmha_fwd() API (#3153 )

* Let fmha_fwd_v3() compatible with fmha_fwd()

* Decouple get_fwd_blobs() and FmhaFwdKernel

* Decouple compatibility checks from get_fwd_blobs()

* Extract product feature checks out from get_fwd_blobs()

* Remove duplicated code in factories and redundant checks

* Remove FmhaFwdKernel<>::GetName()

* Let FmhaFwdApiPool support pipelines with different mask_impl

* Add tile setting for fmha fwd v3 pipeline

* Add fwd v3 instances to tile_example_fmha_fwd manually

* Remove unused function import

* Undo irrelevant changes

* Remove fwd v3 instances from tile_example_fmha_fwd

* Finish fmha fwd v3 kernel instance codegen

* Fix formatting

* Remove unused F_idx attribute

* Add is_generic_attention_mask<> traits

* Add constraints to the fmha fwd v3 pipeline

* Unify traits & problem used for fmha fwd v3

* Unify kernel launch code for fmha fwd v2 & v3

* Unify kernel template selection logic

* Use same kernel codegen template for both v2 & v3

* Rename api() property as render() method

* Allow specifying filter for fmha fwd api pool

* Allow specifying function name when rendering api pool items

* Separate fmha fwd v3 kernel dispatching logic from v2

* Remove lambda assignment

* Add simple v2/v3 dispatch logic

* Stop generating empty if-clauses

Skip iterating over dictionaries that have no traits, and avoid assigning i_* to them.

* Use "".join() to concatenate fmha fwd api string content

* Add more feature checks for fmha fwd v3 pipeline

* Check features before dispatch to fmha_fwd_v3()

* Add more feature checks for fmha_fwd_v3()

* Add missing filter call

* Use Tuple to reserve the dtype orders

* Fix wrong pipeline matching logic

* Add fmha fwd v3 group mode instances

* Add functor_transform<>

* Add type constraints to make_tile_window()

* Remove fmha fwd v3 example

* Fix wrong product(aiter mha_fwd()) config

* Fix wrong fmha fwd v2/v3 selection logic

* Fix formatting

* Add comment to warning v3 kernel users

* Fix wrong codegen logics

* Remove unnecessary param

* Fix format

---------

Co-authored-by: Illia Silin <98187287+illsilin@users.noreply.github.com>

2025-12-05 10:31:12 +08:00

algorithm

[CK_TILE][FMHA] Integrate FAv2 & FAv3 (WIP) in the single fmha_fwd() API (#3153 )

2025-12-05 10:31:12 +08:00

arch

Add validity checks for MoE FlatMM scatter and enable bf16 hardware atomic-add (#3236 )

2025-11-28 09:43:01 +01:00

container

chore(copyright): update copyright header for include directory (#3293 )

2025-11-26 11:00:05 -07:00

numeric

chore(copyright): update copyright header for include directory (#3293 )

2025-11-26 11:00:05 -07:00

tensor

[CK_TILE][FMHA] Integrate FAv2 & FAv3 (WIP) in the single fmha_fwd() API (#3153 )

2025-12-05 10:31:12 +08:00

utility

chore(copyright): update copyright header for include directory (#3293 )

2025-11-26 11:00:05 -07:00

config.hpp

Add support for gfx1153 (#3306 )

2025-11-27 08:48:00 +01:00

README.md

introducing ck_tile! (#1216 )

2024-04-15 19:27:12 -05:00

README.md

ck_tile/core

ck_tile/core contains every basic functions and structures to create a GPU kernel using ck_tile. User should only include ck_tile/core.hpp this single header to use all the functionality. Everything is under ck_tile namespace. The coding style under this folder should be similar to std (snake_case for structure/function, Camel for template types...)

algorithm/
    coordinate transform and some other reusable algorithm
arch/
    contains some basic device building block like mma, buffer addressing, etc...
container/
    contains basic container data structure, array/sequence/tuple/...
numeric/
    data type, and data type related math
tensor/
    tensor descriptors and tile level API
utility/
    other utility function for both host/device