llama.cpp/ggml-sycl.h
Neo Zhang Jianyu 715641391d
Support multiple GPUs (split mode) on SYCL backend (#5806)
* suport multiple cards: split-mode - layer|row

* rm warning

* rebase with master, support tow new OPs, close feature for -sm=row, fix for unit test

* update news

* fix merge error

* update according to review comments
2024-03-02 19:49:30 +08:00

35 lines
1.2 KiB
C

//
// MIT license
// Copyright (C) 2024 Intel Corporation
// SPDX-License-Identifier: MIT
//
#pragma once
#include "ggml.h"
#include "ggml-backend.h"
#ifdef __cplusplus
extern "C" {
#endif
#define GGML_SYCL_MAX_DEVICES 16
#define GGML_SYCL_NAME "SYCL"
GGML_API void ggml_init_sycl(void);
GGML_API bool ggml_sycl_compute_forward(struct ggml_compute_params * params, struct ggml_tensor * tensor);
GGML_API ggml_backend_t ggml_backend_sycl_init(int device);
GGML_API ggml_backend_buffer_type_t ggml_backend_sycl_buffer_type(int device);
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 ggml_backend_buffer_type_t ggml_backend_sycl_split_buffer_type(const float * tensor_split);
GGML_API GGML_CALL void ggml_backend_sycl_get_device_memory(int device, size_t *free, size_t *total);
GGML_API GGML_CALL int ggml_backend_sycl_get_device_index(int device_id);
#ifdef __cplusplus
}
#endif