mirror of
https://github.com/ollama/ollama.git
synced 2025-03-19 22:32:15 +01:00
74 lines
2.8 KiB
C
Vendored
74 lines
2.8 KiB
C
Vendored
/**
|
|
* llama.cpp - commit ba1cb19cdd0d92e012e0f6e009e0620f854b6afd - do not edit this file
|
|
*
|
|
* MIT License
|
|
*
|
|
* Copyright (c) 2023-2024 The ggml authors
|
|
*
|
|
* Permission is hereby granted, free of charge, to any person obtaining a copy
|
|
* of this software and associated documentation files (the "Software"), to deal
|
|
* in the Software without restriction, including without limitation the rights
|
|
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
|
* copies of the Software, and to permit persons to whom the Software is
|
|
* furnished to do so, subject to the following conditions:
|
|
*
|
|
* The above copyright notice and this permission notice shall be included in all
|
|
* copies or substantial portions of the Software.
|
|
*
|
|
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
|
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
|
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
|
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
|
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
|
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
|
* SOFTWARE.
|
|
*/
|
|
|
|
#pragma once
|
|
|
|
#include "ggml.h"
|
|
#include "ggml-backend.h"
|
|
|
|
#ifdef __cplusplus
|
|
extern "C" {
|
|
#endif
|
|
|
|
#ifdef GGML_USE_HIP
|
|
#define GGML_CUDA_NAME "ROCm"
|
|
#define GGML_CUBLAS_NAME "hipBLAS"
|
|
#elif defined(GGML_USE_MUSA)
|
|
#define GGML_CUDA_NAME "MUSA"
|
|
#define GGML_CUBLAS_NAME "muBLAS"
|
|
#else
|
|
#define GGML_CUDA_NAME "CUDA"
|
|
#define GGML_CUBLAS_NAME "cuBLAS"
|
|
#endif
|
|
#define GGML_CUDA_MAX_DEVICES 16
|
|
|
|
// backend API
|
|
GGML_BACKEND_API ggml_backend_t ggml_backend_cuda_init(int device);
|
|
|
|
GGML_BACKEND_API bool ggml_backend_is_cuda(ggml_backend_t backend);
|
|
|
|
// device buffer
|
|
GGML_BACKEND_API ggml_backend_buffer_type_t ggml_backend_cuda_buffer_type(int device);
|
|
|
|
// split tensor buffer that splits matrices by rows across multiple devices
|
|
GGML_BACKEND_API ggml_backend_buffer_type_t ggml_backend_cuda_split_buffer_type(int main_device, const float * tensor_split);
|
|
|
|
// pinned host buffer for use with the CPU backend for faster copies between CPU and GPU
|
|
GGML_BACKEND_API ggml_backend_buffer_type_t ggml_backend_cuda_host_buffer_type(void);
|
|
|
|
GGML_BACKEND_API int ggml_backend_cuda_get_device_count(void);
|
|
GGML_BACKEND_API void ggml_backend_cuda_get_device_description(int device, char * description, size_t description_size);
|
|
GGML_BACKEND_API void ggml_backend_cuda_get_device_memory(int device, size_t * free, size_t * total);
|
|
|
|
GGML_BACKEND_API bool ggml_backend_cuda_register_host_buffer(void * buffer, size_t size);
|
|
GGML_BACKEND_API void ggml_backend_cuda_unregister_host_buffer(void * buffer);
|
|
|
|
GGML_BACKEND_API ggml_backend_reg_t ggml_backend_cuda_reg(void);
|
|
|
|
#ifdef __cplusplus
|
|
}
|
|
#endif
|