[SYCL] supprt Flash Attention for fp32/fp16/Q4/Q5/Q8 (#20190)
* support flash-attention for fp32/fp16/Q4/Q5/Q8 * rm warining * update for JIT
This commit is contained in:
@@ -23,6 +23,7 @@
|
||||
#include "dequantize.hpp"
|
||||
#include "dmmv.hpp"
|
||||
#include "element_wise.hpp"
|
||||
#include "fattn.hpp"
|
||||
#include "gla.hpp"
|
||||
#include "im2col.hpp"
|
||||
#include "mmq.hpp"
|
||||
|
||||
Reference in New Issue
Block a user