Files
candle/candle-flash-attn/kernels/flash_fwd_hdim224_fp16_sm80.cu
Michael Feil 71cd6d5533 Flash-Attn upgrade / SoftCap Candle-FlashAttn [1/n] (#2688)
* update flash-attn v1

* restore: hdim224

* add 224 flash_fwd_template

* remove whitespace
2024-12-31 09:32:22 +01:00

11 lines
392 B
Plaintext

// 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"
#include "flash_fwd_launch_template.h"
template<>
void run_mha_fwd_<cutlass::half_t, 224, false>(Flash_fwd_params &params, cudaStream_t stream) {
run_mha_fwd_hdim224<cutlass::half_t, false>(params, stream);
}