* CUDA: refactor mmq, dmmv, mmvq * fix out-of-bounds write * struct for qk, qr, qi * fix cmake build * mmq_type_traits
10 lines
367 B
Text
10 lines
367 B
Text
// This file has been autogenerated by generate_cu_files.py, do not edit manually.
|
|
|
|
#include "../fattn-wmma-f16.cuh"
|
|
|
|
DECL_FATTN_WMMA_F16_CASE(64, 16, float);
|
|
DECL_FATTN_WMMA_F16_CASE(80, 16, float);
|
|
DECL_FATTN_WMMA_F16_CASE(96, 16, float);
|
|
DECL_FATTN_WMMA_F16_CASE(112, 16, float);
|
|
DECL_FATTN_WMMA_F16_CASE(128, 16, float);
|
|
DECL_FATTN_WMMA_F16_CASE(256, 16, float);
|