llama.cpp/ggml/src/ggml-sycl/backend.hpp
Akarshan Biswas f446c2cf6a
SYCL: Add gated linear attention kernel (#11175)
* SYCL: Add Gated Linear attention kernel

* glahpp: add a space at the end of file

* gla: Put the barrier inside the main logic loop
2025-01-15 11:20:17 +08:00

34 lines
765 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 "concat.hpp"
#include "common.hpp"
#include "conv.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"
#include "tsembd.hpp"
#include "im2col.hpp"
#include "wkv6.hpp"
#include "outprod.hpp"
#include "element_wise.hpp"
#include "gla.hpp"
#endif // GGML_SYCL_BACKEND_HPP