>>> import torch
>>> # torch.mm
>>> a = torch.randn(66, 99)
>>> b = torch.randn(99, 88)
>>> c = torch.mm(a, b)
>>> c.shape
torch.size([66, 88])
>>>
>>> # torch.bmm
>>> a = torch.randn(3, 66, 99)
>>> b = torch.randn(3, 99, 77)
>>> c = torch.bmm(a, b)
>>> c.shape
torch.size([3, 66, 77])
>>>
>>> # torch.mv
>>> a = torch.randn(66, 99)
>>> b = torch.randn(99)
>>> c = torch.mv(a, b)
>>> c.shape
torch.size([66])
>>>
>>> # torch.matmul
>>> a = torch.randn(32, 3, 66, 99)
>>> b = torch.randn(32, 3, 99, 55)
>>> c = torch.matmul(a, b)
>>> c.shape
torch.size([32, 3, 66, 55])
>>>
>>> # @
>>> d = a @ b
>>> d.shape
torch.size([32, 3, 66, 55])

//!
//! \brief Add a MatrixMultiply layer to the network.
//!
//! \param input0 The first input tensor (commonly A).
//! \param op0 The operation to apply to input0.
//! \param input1 The second input tensor (commonly B).
//! \param op1 The operation to apply to input1.
//!
//! \see IMatrixMultiplyLayer
//!
//! \warning Int32 tensors are not valid input tensors.
//!
//! \return The new matrix multiply layer, or nullptr if it could not be created.
//!
IMatrixMultiplyLayer* addMatrixMultiply(
  ITensor& input0, MatrixOperation op0, ITensor& input1, MatrixOperation op1) noexcept
{
  return mImpl->addMatrixMultiply(input0, op0, input1, op1);
}

// 構造張量 Tensor0
nvinfer1::IConstantLayer *Constant_layer0 = m_network->addConstant(tensorShape0, value0);
// 構造張量 Tensor1
nvinfer1::IConstantLayer *Constant_layer1 = m_network->addConstant(tensorShape1, value1);

// 添加矩陣乘法
nvinfer1::IMatrixMultiplyLayer *Matmul_layer = m_network->addMatrixMultiply(Constant_layer0->getOutput(0), matrix0Type, Constant_layer1->getOutput(0), matrix2Type);

// 獲取輸出
matmulOutput = Matmul_layer->getOputput(0);

>>> import torch
>>> # torch.mul
>>> a = torch.randn(66, 99)
>>> b = torch.randn(66, 99)
>>> c = torch.mul(a, b)
>>> c.shape
torch.size([66, 99])
>>> d = 0.125
>>> e = torch.mul(a, d)
>>> e.shape
torch.size([66, 99])
>>> # *
>>> f = a * b
>>> f.shape
torch.size([66, 99])

//!
//! \brief Add a Scale layer to the network.
//!
//! \param input The input tensor to the layer.
//!              This tensor is required to have a minimum of 3 dimensions in implicit batch mode
//!              and a minimum of 4 dimensions in explicit batch mode.
//! \param mode The scaling mode.
//! \param shift The shift value.
//! \param scale The scale value.
//! \param power The power value.
//!
//! If the weights are available, then the size of weights are dependent on the ScaleMode.
//! For ::kUNIFORM, the number of weights equals 1.
//! For ::kCHANNEL, the number of weights equals the channel dimension.
//! For ::kELEMENTWISE, the number of weights equals the product of the last three dimensions of the input.
//!
//! \see addScaleNd
//! \see IScaleLayer
//! \warning Int32 tensors are not valid input tensors.
//!
//! \return The new Scale layer, or nullptr if it could not be created.
//!
IScaleLayer* addScale(ITensor& input, ScaleMode mode, Weights shift, Weights scale, Weights power) noexcept
{
  return mImpl->addScale(input, mode, shift, scale, power);
}

// 構造張量 input
nvinfer1::IConstantLayer *Constant_layer = m_network->addConstant(tensorShape, value);

// scalemode選擇，kUNIFORM、kCHANNEL、kELEMENTWISE
scalemode = kUNIFORM;

// 構建 Weights 類型的 shift、scale、power，其中 volume 為元素數量
nvinfer1::Weights scaleShift{nvinfer1::DataType::kFLOAT, nullptr, volume };
nvinfer1::Weights scaleScale{nvinfer1::DataType::kFLOAT, nullptr, volume };
nvinfer1::Weights scalePower{nvinfer1::DataType::kFLOAT, nullptr, volume };

// !! 注意這里還需要對 shift、scale、power 的 values 進行賦值，若只是乘法只需要對 scale 進行賦值就行

// 添加張量乘法
nvinfer1::IScaleLayer *Scale_layer = m_network->addScale(Constant_layer->getOutput(0), scalemode, scaleShift, scaleScale, scalePower);

// 獲取輸出
scaleOutput = Scale_layer->getOputput(0);