mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-11-14 11:07:10 +00:00
b260213755
* refactor to support soft_max_ext * fix error and support soft_max_back * rm unused functions * fix format issue --------- Co-authored-by: Zhang Jianyu <zhang.jianyu@outlook.com>
25 lines
622 B
C++
25 lines
622 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_SOFTMAX_HPP
|
|
#define GGML_SYCL_SOFTMAX_HPP
|
|
|
|
#include "common.hpp"
|
|
|
|
#define SYCL_SOFT_MAX_BLOCK_SIZE 1024
|
|
|
|
void ggml_sycl_op_soft_max(ggml_backend_sycl_context &ctx, ggml_tensor *dst);
|
|
|
|
void ggml_sycl_op_soft_max_back(ggml_backend_sycl_context & ctx, ggml_tensor * dst);
|
|
|
|
#endif // GGML_SYCL_SOFTMAX_HPP
|