mirror of
https://github.com/deepseek-ai/FlashMLA
synced 2025-06-26 18:15:54 +00:00
4 lines
172 B
Plaintext
4 lines
172 B
Plaintext
#include "flash_fwd_mla_kernel.h"
|
|
|
|
template void run_mha_fwd_splitkv_mla<cutlass::bfloat16_t, cutlass::bfloat16_t, 576>(Flash_fwd_mla_params ¶ms, cudaStream_t stream);
|