| // 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" | |
| template<> | |
| void run_mha_bwd_<80, cutlass::bfloat16_t, 96, false>(Flash_bwd_params ¶ms, cudaStream_t stream) { | |
| run_mha_bwd_hdim96<80, cutlass::bfloat16_t, false>(params, stream); | |
| } | |
| template<> | |
| void run_mha_bwd_<86, cutlass::bfloat16_t, 96, false>(Flash_bwd_params ¶ms, cudaStream_t stream) { | |
| run_mha_bwd_hdim96<86, cutlass::bfloat16_t, false>(params, stream); | |
| } | |