mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-07-15 15:17:44 +00:00
704bb7a71c
* SYCL: Initial set_rows kernel implementation * Revert max_threads to 256 * Refactor set_rows and address review comments * Deduplicate conversion function * Remove guard before kernel launch and refactor * Fix and add back SFINAE
39 lines
854 B
C++
39 lines
854 B
C++
//
|
|
// MIT license
|
|
// Copyright (C) 2024 Intel Corporation
|
|
// SPDX-License-Identifier: MIT
|
|
//
|
|
|
|
//
|
|
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
|
|
// See https://llvm.org/LICENSE.txt for license information.
|
|
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
|
|
//
|
|
|
|
#ifndef GGML_SYCL_BACKEND_HPP
|
|
#define GGML_SYCL_BACKEND_HPP
|
|
|
|
#include "binbcast.hpp"
|
|
#include "common.hpp"
|
|
#include "concat.hpp"
|
|
#include "conv.hpp"
|
|
#include "convert.hpp"
|
|
#include "cpy.hpp"
|
|
#include "dequantize.hpp"
|
|
#include "dmmv.hpp"
|
|
#include "element_wise.hpp"
|
|
#include "gla.hpp"
|
|
#include "im2col.hpp"
|
|
#include "mmq.hpp"
|
|
#include "mmvq.hpp"
|
|
#include "norm.hpp"
|
|
#include "outprod.hpp"
|
|
#include "quants.hpp"
|
|
#include "rope.hpp"
|
|
#include "set_rows.hpp"
|
|
#include "softmax.hpp"
|
|
#include "tsembd.hpp"
|
|
#include "wkv.hpp"
|
|
|
|
#endif // GGML_SYCL_BACKEND_HPP
|