Skip to content

Commit 2f34b86

Browse files
slarenslaren
authored
cuda : fix LLAMA_CUDA_F16 build (ggml-org#6298)
1 parent ae1f211 commit 2f34b86

File tree

1 file changed

+1
-0
lines changed

1 file changed

+1
-0
lines changed

‎ggml-cuda/dmmv.cu

+1
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,6 @@
11
#include "dmmv.cuh"
22
#include "dequantize.cuh"
3+
#include "convert.cuh"
34

45
// dmmv = dequantize_mul_mat_vec
56
#ifndef GGML_CUDA_DMMV_X

0 commit comments

Comments
 (0)