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>
20 lines
717 B
Text
20 lines
717 B
Text
#pragma once
|
|
|
|
#include "common.cuh"
|
|
#include "mmq.cuh"
|
|
|
|
#include <cstdint>
|
|
|
|
#define CUDA_QUANTIZE_BLOCK_SIZE 256
|
|
|
|
typedef void (*quantize_cuda_t)(
|
|
const float * x, void * vy, const int64_t kx0, const int64_t kx1, const int64_t channels, const int64_t kx0_padded,
|
|
const ggml_type type_x, cudaStream_t stream);
|
|
|
|
void quantize_row_q8_1_cuda(
|
|
const float * x, void * vy, const int64_t kx0, const int64_t kx1, const int64_t channels, const int64_t kx0_padded,
|
|
const ggml_type type_x, cudaStream_t stream);
|
|
|
|
void quantize_mmq_q8_1_cuda(
|
|
const float * x, void * vy, const int64_t kx0, const int64_t kx1, const int64_t channels, const int64_t kx0_padded,
|
|
const ggml_type type_x, cudaStream_t stream);
|