mirror of
https://github.com/deepseek-ai/FlashMLA
synced 2025-06-26 18:15:54 +00:00
7 lines
150 B
C++
7 lines
150 B
C++
#pragma once
|
|
|
|
#include "flash_mla.h"
|
|
|
|
template<typename InputT>
|
|
void run_flash_splitkv_mla_kernel(Flash_fwd_mla_params ¶ms, cudaStream_t stream);
|