ExternalVendorCode/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/whisper.cpp.git synced 2025-06-19 07:18:07 +00:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity

whisper : initial hipBLAS support (#1209)

Browse Source
This commit is contained in:
ardfork
2023-08-27 17:03:58 +00:00
committed by GitHub
parent b5bb5c85d4
commit cb5fb0a12d
3 changed files with 98 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

51
ggml-cuda.cu
View File

@ -6,9 +6,60 @@
#include <atomic>
#include <assert.h>
#if defined(GGML_USE_HIPBLAS)
#include <hip/hip_runtime.h>
#include <hipblas/hipblas.h>
#include <hip/hip_fp16.h>
#include <rocblas/rocblas.h>
#define CUBLAS_OP_N HIPBLAS_OP_N
#define CUBLAS_OP_T HIPBLAS_OP_T
#define CUBLAS_STATUS_SUCCESS HIPBLAS_STATUS_SUCCESS
#define CUBLAS_TF32_TENSOR_OP_MATH 0
#define __shfl_xor_sync(mask, var, laneMask, width) __shfl_xor(var, laneMask, width)
#define cublasCreate hipblasCreate
#define cublasGetStatusString rocblas_status_to_string
#define cublasHandle_t hipblasHandle_t
#define cublasLoggerConfigure(logIsOn, logToStdOut, logToStdErr, logFileName) CUBLAS_STATUS_SUCCESS
#define cublasSetMathMode(handle, mode) CUBLAS_STATUS_SUCCESS
#define cublasSetStream hipblasSetStream
#define cublasSgemm hipblasSgemm
#define cublasStatus_t hipblasStatus_t
#define cudaDeviceProp hipDeviceProp_t
#define cudaDeviceSynchronize hipDeviceSynchronize
#define cudaError_t hipError_t
#define cudaEventCreateWithFlags hipEventCreateWithFlags
#define cudaEventDestroy hipEventDestroy
#define cudaEventDisableTiming hipEventDisableTiming
#define cudaEventRecord hipEventRecord
#define cudaEvent_t hipEvent_t
#define cudaFree hipFree
#define cudaFreeHost hipHostFree
#define cudaGetDevice hipGetDevice
#define cudaGetDeviceCount hipGetDeviceCount
#define cudaGetDeviceProperties hipGetDeviceProperties
#define cudaGetErrorString hipGetErrorString
#define cudaGetLastError hipGetLastError
#define cudaMalloc hipMalloc
#define cudaMallocHost hipHostMalloc
#define cudaMemcpy hipMemcpy
#define cudaMemcpy2DAsync hipMemcpy2DAsync
#define cudaMemcpyAsync hipMemcpyAsync
#define cudaMemcpyDeviceToDevice hipMemcpyDeviceToDevice
#define cudaMemcpyDeviceToHost hipMemcpyDeviceToHost
#define cudaMemcpyHostToDevice hipMemcpyHostToDevice
#define cudaMemcpyKind hipMemcpyKind
#define cudaMemset hipMemset
#define cudaSetDevice hipSetDevice
#define cudaStreamCreateWithFlags hipStreamCreateWithFlags
#define cudaStreamNonBlocking hipStreamNonBlocking
#define cudaStreamWaitEvent(stream, event) hipStreamWaitEvent(stream, event, 0)
#define cudaStream_t hipStream_t
#define cudaSuccess hipSuccess
#else
#include <cuda_runtime.h>
#include <cublas_v2.h>
#include <cuda_fp16.h>
#endif
#include "ggml-cuda.h"
#include "ggml.h"