mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-10-31 08:51:55 +00:00
7a32fcb3b2
* ggml : add Q8_0 quantization format (rename the old one to Q8_1) * tests : fix test-quantize-fns * ggml : finalize Q8_0 implementation * ggml : use q4_0_q8_0 and q4_2_q8_0 * ggml : fix Q8_0 dot product bug (ARM) * ggml : Q8_0 unroll x2 * ggml : fix bug - using wrong block type * ggml : extend quantize_fns_t with "vec_dot_type" * ggml : fix Q8_0 to use 255 values out of 256 * ggml : fix assert using wrong QK4_2 instead of QK4_3
43 lines
2.1 KiB
C
43 lines
2.1 KiB
C
#include <cublas_v2.h>
|
|
#include <cuda_runtime.h>
|
|
|
|
#ifdef __cplusplus
|
|
extern "C" {
|
|
#endif
|
|
|
|
#define CUDA_CHECK(err) \
|
|
do { \
|
|
cudaError_t err_ = (err); \
|
|
if (err_ != cudaSuccess) { \
|
|
fprintf(stderr, "CUDA error %d at %s:%d: %s\n", err_, __FILE__, __LINE__, \
|
|
cudaGetErrorString(err_)); \
|
|
exit(1); \
|
|
} \
|
|
} while (0)
|
|
|
|
#define CUBLAS_CHECK(err) \
|
|
do { \
|
|
cublasStatus_t err_ = (err); \
|
|
if (err_ != CUBLAS_STATUS_SUCCESS) { \
|
|
fprintf(stderr, "cuBLAS error %d at %s:%d\n", err_, __FILE__, __LINE__); \
|
|
exit(1); \
|
|
} \
|
|
} while (0)
|
|
|
|
extern cublasHandle_t g_cublasH;
|
|
extern cudaStream_t g_cudaStream;
|
|
|
|
void ggml_init_cublas(void);
|
|
void * ggml_cuda_pool_malloc(size_t size, size_t * actual_size);
|
|
void ggml_cuda_pool_free(void * ptr, size_t size);
|
|
|
|
void dequantize_row_q4_0_cuda(const void * vx, float * y, int k, cudaStream_t stream);
|
|
void dequantize_row_q4_1_cuda(const void * vx, float * y, int k, cudaStream_t stream);
|
|
void dequantize_row_q4_2_cuda(const void * vx, float * y, int k, cudaStream_t stream);
|
|
void dequantize_row_q4_3_cuda(const void * vx, float * y, int k, cudaStream_t stream);
|
|
void dequantize_row_q8_0_cuda(const void * vx, float * y, int k, cudaStream_t stream);
|
|
|
|
#ifdef __cplusplus
|
|
}
|
|
#endif
|