mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2025-03-06 20:48:53 +01:00
5 lines
188 B
Text
5 lines
188 B
Text
#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);
|