File size: 523 Bytes
eb8ddce |
1 2 3 4 5 6 7 8 9 10 11 12 13 |
// 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_HDIM192
template<>
void run_mha_bwd_<90, cutlass::half_t, 192, true>(Flash_bwd_params ¶ms, cudaStream_t stream) {
run_mha_bwd_hdim192<90, cutlass::half_t, true>(params, stream);
}
#endif
|