Sigbjørn Skjæret
36ca8b3628
* add bf16 support * use convert_from_bf16_cuda instead of convert_unary_cuda for f32 * revert 7ec5085 * move functionality into convert_unary with constexpr
17 lines
495 B
Plaintext
17 lines
495 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, int64_t k, cudaStream_t stream);
|
|
|
|
typedef to_t_cuda_t<float> to_fp32_cuda_t;
|
|
typedef to_t_cuda_t<half> to_fp16_cuda_t;
|
|
typedef to_t_cuda_t<nv_bfloat16> to_bf16_cuda_t;
|
|
|
|
to_fp16_cuda_t ggml_get_to_fp16_cuda(ggml_type type);
|
|
|
|
to_bf16_cuda_t ggml_get_to_bf16_cuda(ggml_type type);
|
|
|
|
to_fp32_cuda_t ggml_get_to_fp32_cuda(ggml_type type);
|