mirror of
https://github.com/dogkeeper886/ollama37.git
synced 2025-12-13 17:27:05 +00:00
dcfb7a105c
* add build to .dockerignore * test: only build one arch * add build to .gitignore * fix ccache path * filter amdgpu targets * only filter if autodetecting * Don't clobber gpu list for default runner This ensures the GPU specific environment variables are set properly * explicitly set CXX compiler for HIP * Update build_windows.ps1 This isn't complete, but is close. Dependencies are missing, and it only builds the "default" preset. * build: add ollama subdir * add .git to .dockerignore * docs: update development.md * update build_darwin.sh * remove unused scripts * llm: add cwd and build/lib/ollama to library paths * default DYLD_LIBRARY_PATH to LD_LIBRARY_PATH in runner on macOS * add additional cmake output vars for msvc * interim edits to make server detection logic work with dll directories like lib/ollama/cuda_v12 * remove unncessary filepath.Dir, cleanup * add hardware-specific directory to path * use absolute server path * build: linux arm * cmake install targets * remove unused files * ml: visit each library path once * build: skip cpu variants on arm * build: install cpu targets * build: fix workflow * shorter names * fix rocblas install * docs: clean up development.md * consistent build dir removal in development.md * silence -Wimplicit-function-declaration build warnings in ggml-cpu * update readme * update development readme * llm: update library lookup logic now that there is one runner (#8587) * tweak development.md * update docs * add windows cuda/rocm tests --------- Co-authored-by: jmorganca <jmorganca@gmail.com> Co-authored-by: Daniel Hiltgen <daniel@ollama.com>
50 lines
1.7 KiB
C
Vendored
50 lines
1.7 KiB
C
Vendored
//
|
|
// 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_BACKEND_API ggml_backend_t ggml_backend_sycl_init(int device);
|
|
|
|
GGML_BACKEND_API bool ggml_backend_is_sycl(ggml_backend_t backend);
|
|
|
|
// devide buffer
|
|
GGML_BACKEND_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_BACKEND_API 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_BACKEND_API ggml_backend_buffer_type_t ggml_backend_sycl_host_buffer_type(void);
|
|
|
|
GGML_BACKEND_API void ggml_backend_sycl_print_sycl_devices(void);
|
|
GGML_BACKEND_API void ggml_backend_sycl_get_gpu_list(int *id_list, int max_len);
|
|
GGML_BACKEND_API void ggml_backend_sycl_get_device_description(int device,
|
|
char *description,
|
|
size_t description_size);
|
|
GGML_BACKEND_API int ggml_backend_sycl_get_device_count();
|
|
GGML_BACKEND_API 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_BACKEND_API bool ggml_backend_sycl_register_host_buffer(void * buffer, size_t size);
|
|
// GGML_BACKEND_API void ggml_backend_sycl_unregister_host_buffer(void * buffer);
|
|
|
|
GGML_BACKEND_API ggml_backend_reg_t ggml_backend_sycl_reg(void);
|
|
|
|
#ifdef __cplusplus
|
|
}
|
|
#endif
|