mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-12-30 21:34:36 +00:00
6 lines
188 B
Plaintext
6 lines
188 B
Plaintext
|
#include "common.cuh"
|
||
|
|
|
||
|
|
#define CUDA_QUANTIZE_BLOCK_SIZE 256
|
||
|
|
|
||
|
|
void quantize_row_q8_1_cuda(const float * x, void * vy, const int kx, const int ky, const int kx_padded, cudaStream_t stream);
|