// Copyright (c) 2024, Tri Dao. | |
// Splitting the different head dimensions to different files to speed up compilation. | |
// This file is auto-generated. See "generate_kernels.py" | |
namespace FLASH_NAMESPACE { | |
template<> | |
void run_mha_bwd_<cutlass::half_t, 96, false>(Flash_bwd_params ¶ms, cudaStream_t stream) { | |
run_mha_bwd_hdim96<cutlass::half_t, false>(params, stream); | |
} | |
} // namespace FLASH_NAMESPACE |