f3f65429c4
* scripts : update sync [no ci] * files : relocate [no ci] * ci : disable kompute build [no ci] * cmake : fixes [no ci] * server : fix mingw build ggml-ci * cmake : minor [no ci] * cmake : link math library [no ci] * cmake : build normal ggml library (not object library) [no ci] * cmake : fix kompute build ggml-ci * make,cmake : fix LLAMA_CUDA + replace GGML_CDEF_PRIVATE ggml-ci * move public backend headers to the public include directory (#8122) * move public backend headers to the public include directory * nix test * spm : fix metal header --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> * scripts : fix sync paths [no ci] * scripts : sync ggml-blas.h [no ci] --------- Co-authored-by: slaren <slarengh@gmail.com>
13 lines
391 B
Text
13 lines
391 B
Text
#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;
|
|
|
|
to_fp16_cuda_t ggml_get_to_fp16_cuda(ggml_type type);
|
|
|
|
to_fp32_cuda_t ggml_get_to_fp32_cuda(ggml_type type);
|