parallelize fattn compilation test
This commit is contained in:
parent
f4003cfba1
commit
1ca802a3e0
6 changed files with 390 additions and 288 deletions
5
ggml-cuda/fattn-vec-f16-q4_0-q4_0.cu
Normal file
5
ggml-cuda/fattn-vec-f16-q4_0-q4_0.cu
Normal file
|
@ -0,0 +1,5 @@
|
|||
#include "common.cuh"
|
||||
#include "fattn-common.cuh"
|
||||
#include "fattn-vec-f16.cuh"
|
||||
|
||||
DECL_FATTN_VEC_INST(f16, 128, 1, 4, q4_0, q4_0);
|
Loading…
Add table
Add a link
Reference in a new issue