mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-11-15 07:19:53 +00:00
d08c20edde
* use warp_size macro for all sycl kernels * fix mask of permute_sub_group_by_xor * fix rms_norm with correct warp number * fix rms_norm_f32/group_norm_f32 * move norm to norm.cpp file * fix quantize bug * fix mmvq's batch size
26 lines
566 B
C++
26 lines
566 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"
|
|
|
|
#endif // GGML_SYCL_BACKEND_HPP
|