mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2025-02-05 16:10:42 +01:00
a9554e20b6
* fix group_norm ut * split softmax * fix softmax * add concat support condition * revert debug code * move QK_WARP_SIZE to presets.hpp
27 lines
589 B
C++
27 lines
589 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 "common.hpp"
|
|
#include "convert.hpp"
|
|
#include "dequantize.hpp"
|
|
#include "dmmv.hpp"
|
|
#include "mmq.hpp"
|
|
#include "mmvq.hpp"
|
|
#include "rope.hpp"
|
|
#include "norm.hpp"
|
|
#include "softmax.hpp"
|
|
|
|
#endif // GGML_SYCL_BACKEND_HPP
|