vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

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
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
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
}