AesSedaiandGitHub
046e284437
* mimo-v2.5: add flash attention mma/tiles for for d_kq=192 d_v=128 * mimo-v2.5: follow (256, 256) fattn templates * mimo-v2.5: cleanup comments * mimo-v2.5: further comment cleanup * mimo-v2.5: address PR feedback fix GQA handling check for other dangling 320/576 carveouts and mirror them for 192 Add to backend ops test so new paths are covered
13 lines
439 B
Plaintext
13 lines
439 B
Plaintext
// This file has been autogenerated by generate_cu_files.py, do not edit manually.
|
|
|
|
#include "../fattn-mma-f16.cuh"
|
|
|
|
DECL_FATTN_MMA_F16_CASE(64, 64, 8, 8);
|
|
DECL_FATTN_MMA_F16_CASE(80, 80, 8, 8);
|
|
DECL_FATTN_MMA_F16_CASE(96, 96, 8, 8);
|
|
DECL_FATTN_MMA_F16_CASE(112, 112, 8, 8);
|
|
DECL_FATTN_MMA_F16_CASE(128, 128, 8, 8);
|
|
DECL_FATTN_MMA_F16_CASE(192, 128, 8, 8);
|
|
DECL_FATTN_MMA_F16_CASE(256, 256, 8, 8);
|
|
DECL_FATTN_MMA_F16_CASE(512, 512, 8, 8);
|