File size: 741 Bytes
4d1b54e |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 |
// Copyright (c) 2024, Jay Shah, Ganesh Bikshandi, Ying Zhang, Vijay Thakkar, Pradeep Ramani, Tri Dao.
// Splitting the different template instantiations to different files to speed up compilation.
// This file is auto-generated. See "generate_kernels.py"
#include "flash_bwd_launch_template.h"
#ifndef FLASHATTENTION_DISABLE_SM8x
#ifndef FLASHATTENTION_DISABLE_HDIM64
template<>
void run_mha_bwd_<80, cutlass::half_t, 64, true>(Flash_bwd_params ¶ms, cudaStream_t stream) {
run_mha_bwd_hdim64<80, cutlass::half_t, true>(params, stream);
}
template<>
void run_mha_bwd_<86, cutlass::half_t, 64, true>(Flash_bwd_params ¶ms, cudaStream_t stream) {
run_mha_bwd_hdim64<86, cutlass::half_t, true>(params, stream);
}
#endif
#endif
|