mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2025-01-09 12:08:56 +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
25 lines
652 B
C++
25 lines
652 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"
|
|
|
|
void ggml_sycl_op_soft_max(ggml_backend_sycl_context &ctx, const ggml_tensor *src0,
|
|
const ggml_tensor *src1, ggml_tensor *dst,
|
|
const float *src0_dd, const float *src1_dd,
|
|
float *dst_dd,
|
|
const queue_ptr &main_stream);
|
|
|
|
#endif // GGML_SYCL_SOFTMAX_HPP
|