tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-30 04:45:17 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add Q4_3 support to cuBLAS (#1086)

Browse Source
This commit is contained in:
slaren
2023-04-20 20:49:53 +02:00
committed by GitHub
parent 8a1756abdf
commit 2005469ea1
3 changed files with 41 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
ggml-cuda.h
View File

@ -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
}