mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-12-26 14:20:31 +01:00
12 lines
332 B
C
12 lines
332 B
C
|
#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
|