mirror of
https://github.com/ikawrakow/ik_llama.cpp.git
synced 2026-04-30 03:11:51 +00:00
20 lines
570 B
C
20 lines
570 B
C
#pragma once
|
|
|
|
#include <cuda_runtime.h>
|
|
#include <cuda.h>
|
|
#include <cublas_v2.h>
|
|
#include <cuda_fp16.h>
|
|
#include <cuda_bf16.h>
|
|
|
|
#if CUDART_VERSION >= 12050
|
|
#include <cuda_fp8.h>
|
|
#endif // CUDART_VERSION >= 12050
|
|
|
|
#if CUDART_VERSION < 11020
|
|
#define CU_DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED CU_DEVICE_ATTRIBUTE_VIRTUAL_ADDRESS_MANAGEMENT_SUPPORTED
|
|
#define CUBLAS_TF32_TENSOR_OP_MATH CUBLAS_TENSOR_OP_MATH
|
|
#define CUBLAS_COMPUTE_16F CUDA_R_16F
|
|
#define CUBLAS_COMPUTE_32F CUDA_R_32F
|
|
#define cublasComputeType_t cudaDataType_t
|
|
#endif // CUDART_VERSION < 11020
|