tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-07-01 05:05:10 +00:00
Code Issues Packages Projects Releases Wiki Activity

Improve cuBLAS performance by dequantizing on the GPU (#1065)

Browse Source
This commit is contained in:
slaren
2023-04-20 03:14:14 +02:00
committed by GitHub
parent 834695fe3a
commit 02d6988121
5 changed files with 221 additions and 41 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
ggml-cuda.h Normal file
View File

@ -0,0 +1,11 @@
#ifdef __cplusplus
extern "C" {
#endif
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);
#ifdef __cplusplus
}
#endif