mirror of
https://github.com/ggerganov/whisper.cpp.git
synced 2024-12-22 22:12:21 +00:00
2948c740a2
* sync : update scripts * sync : ggml * talk-llama : sync llama.cpp * make : WHISPER_CUBLAS -> WHISPER_CUDA * ci : try to fix sycl build * talk-llama : fix make build
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);
|