Add Q4_3 support to cuBLAS (#1086)

2023-04-20 20:49:53 +02:00
parent 8a1756abdf
commit 2005469ea1
3 changed files with 41 additions and 2 deletions
--- a/ggml-cuda.h
+++ b/ggml-cuda.h
@@ -5,6 +5,7 @@ extern "C" {
 void dequantize_row_q4_0_cuda(const void * vx, float * y, int k, cudaStream_t stream);
 void dequantize_row_q4_1_cuda(const void * vx, float * y, int k, cudaStream_t stream);
 void dequantize_row_q4_2_cuda(const void * vx, float * y, int k, cudaStream_t stream);
+void dequantize_row_q4_3_cuda(const void * vx, float * y, int k, cudaStream_t stream);

 #ifdef  __cplusplus
 }