mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-12-27 03:44:35 +00:00
14 lines
387 B
Plaintext
14 lines
387 B
Plaintext
|
#include "common.cuh"
|
||
|
|
|
||
|
|
#define CUDA_DEQUANTIZE_BLOCK_SIZE 256
|
||
|
|
|
||
|
|
template<typename T>
|
||
|
|
using to_t_cuda_t = void (*)(const void * __restrict__ x, T * __restrict__ y, int k, cudaStream_t stream);
|
||
|
|
|
||
|
|
typedef to_t_cuda_t<float> to_fp32_cuda_t;
|
||
|
|
typedef to_t_cuda_t<half> to_fp16_cuda_t;
|
||
|
|
|
||
|
|
to_fp16_cuda_t ggml_get_to_fp16_cuda(ggml_type type);
|
||
|
|
|
||
|
|
to_fp32_cuda_t ggml_get_to_fp32_cuda(ggml_type type);
|