Files
enginex-ascend-910-vllm/csrc/attention/compressor/op_kernel/arch32/soft_max.h
Sun Ruoxi 7f8a1b1f7a init v0.23.0
Signed-off-by: Sun Ruoxi <sunruoxi@4paradigm.com>
2026-08-27 15:11:51 +08:00

53 lines
2.0 KiB
C++
Raw Blame History

This file contains invisible Unicode characters

This file contains invisible Unicode characters that are indistinguishable to humans but may be processed differently by a computer. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

/**
 * Copyright (c) 2026 Huawei Technologies Co., Ltd.
 * This program is free software, you can redistribute it and/or modify it under the terms and conditions of
 * CANN Open Software License Agreement Version 2.0 (the "License").
 * Please refer to the License for details. You may not use this file except in compliance with the License.
 * THIS SOFTWARE IS PROVIDED ON AN "AS IS" BASIS, WITHOUT WARRANTIES OF ANY KIND, EITHER EXPRESS OR IMPLIED,
 * INCLUDING BUT NOT LIMITED TO NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE.
 * See LICENSE in the root of the software repository for the full text of the License.
 */
/*!
* \file soft_max.h
* \brief
*/
#ifndef SOFT_MAX_H
#define SOFT_MAX_H
#include "compressor_comm.h"
#include "compressor_vector_comm.h"
namespace Compressor {
/**
* @brief ColumnSoftMax 对矩阵按列进行SoftMax
* @param dstLocal 输出tensor [row, col]支持和srcLocal是同一块空间
* @param srcLocal 输入tensor [row, col]
* @param shareTmpUb 临时buffer 内部需要的空间为 [floor(row / 2) * col * sizeof(float)]
* @param row 行数
* @param col 列数
*/
__aicore__ inline void ColumnSoftMax(const LocalTensor<float> &dstLocal, const LocalTensor<float> &srcLocal,
const LocalTensor<float> &shareTmpUb, uint32_t row, uint32_t col)
{
uint32_t dtypeMask = FP32_REPEAT_ELEMENT_NUM;
uint32_t dLoop = col / dtypeMask;
uint32_t dRemain = col % dtypeMask;
uint8_t repeatStride = col / FP32_BLOCK_ELEMENT_NUM;
ColumnMax(shareTmpUb, srcLocal, shareTmpUb, row, col);
PipeBarrier<PIPE_V>();
MatSubVec(dstLocal, srcLocal, shareTmpUb, {row, col, dtypeMask, dLoop, dRemain, repeatStride});
PipeBarrier<PIPE_V>();
Exp(dstLocal, dstLocal, row * col);
PipeBarrier<PIPE_V>();
ColumnSum(shareTmpUb, dstLocal, shareTmpUb, row, col);
PipeBarrier<PIPE_V>();
MatDivVec(dstLocal, dstLocal, shareTmpUb, {row, col, dtypeMask, dLoop, dRemain, repeatStride});
}
} // namespace Compressor
#endif