flash_fwd_hdim64_bf16_paged_packgqa_sm90.cu 472 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_HDIM64
  6. template void run_mha_fwd_<90, cutlass::bfloat16_t, 64, false, true, false, true>(Flash_fwd_params &params, cudaStream_t stream);
  7. #endif