mirror of
https://github.com/huggingface/candle.git
synced 2025-06-15 18:28:24 +00:00
71cd6d5533
* update flash-attn v1 * restore: hdim224 * add 224 flash_fwd_template * remove whitespace
11 lines
390 B
Plaintext
11 lines
390 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, 160, true>(Flash_fwd_params ¶ms, cudaStream_t stream) {
|
|
run_mha_fwd_hdim160<cutlass::half_t, true>(params, stream);
|
|
}
|