flash_fwd_hdim192_bf16_split_softcap_packgqa_sm90.cu 473 B

123456789
  1. // Copyright (c) 2024, Jay Shah, Ganesh Bikshandi, Ying Zhang, Vijay Thakkar, Pradeep Ramani, Tri Dao.
  2. // Splitting the different template instantiations to different files to speed up compilation.
  3. // This file is auto-generated. See "generate_kernels.py"
  4. #include "flash_fwd_launch_template.h"
  5. #ifndef FLASHATTENTION_DISABLE_HDIM192
  6. template void run_mha_fwd_<90, cutlass::bfloat16_t, 192, true, false, true, true>(Flash_fwd_params &params, cudaStream_t stream);
  7. #endif