mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-12-30 16:07:17 +01:00
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>
43 lines
1.5 KiB
C
43 lines
1.5 KiB
C
//
|
|
// MIT license
|
|
// Copyright (C) 2024 Intel Corporation
|
|
// SPDX-License-Identifier: MIT
|
|
//
|
|
|
|
#pragma once
|
|
|
|
#include "ggml.h"
|
|
#include "ggml-backend.h"
|
|
|
|
#define GGML_SYCL_NAME "SYCL"
|
|
#define GGML_SYCL_MAX_DEVICES 48
|
|
|
|
#ifdef __cplusplus
|
|
extern "C" {
|
|
#endif
|
|
|
|
// backend API
|
|
GGML_API ggml_backend_t ggml_backend_sycl_init(int device);
|
|
|
|
// devide buffer
|
|
GGML_API ggml_backend_buffer_type_t ggml_backend_sycl_buffer_type(int device);
|
|
|
|
// split tensor buffer that splits matrices by rows across multiple devices
|
|
GGML_API GGML_CALL ggml_backend_buffer_type_t ggml_backend_sycl_split_buffer_type(const float * tensor_split);
|
|
|
|
// pinned host buffer for use with the CPU backend for faster copies between CPU and GPU
|
|
GGML_API ggml_backend_buffer_type_t ggml_backend_sycl_host_buffer_type(void);
|
|
|
|
GGML_API void ggml_backend_sycl_print_sycl_devices(void);
|
|
GGML_API GGML_CALL void ggml_sycl_get_gpu_list(int *id_list, int max_len);
|
|
GGML_API GGML_CALL void ggml_sycl_get_device_description(int device, char *description, size_t description_size);
|
|
GGML_API GGML_CALL int ggml_backend_sycl_get_device_count();
|
|
GGML_API GGML_CALL void ggml_backend_sycl_get_device_memory(int device, size_t *free, size_t *total);
|
|
|
|
// SYCL doesn't support registering host memory, keep here for reference
|
|
// GGML_API GGML_CALL bool ggml_backend_sycl_register_host_buffer(void * buffer, size_t size);
|
|
// GGML_API GGML_CALL void ggml_backend_sycl_unregister_host_buffer(void * buffer);
|
|
#ifdef __cplusplus
|
|
}
|
|
#endif
|