NVIDIA TensorRT Operators Documentation
8.6.0
Activation
Assertion
Concatenation
Constant
Convolution
Deconvolution
Dequantize
Einsum
ElementWise
Fill
FullyConnected
Gather
GridSample
Identity
If
LRN
Loop
MatrixMultiply
NMS
NonZero
Normalization
Padding
ParametricReLU
PluginV2
Pooling
Quantize
RNN
RaggedSoftMax
Reduce
Resize
ReverseSequence
Scale
Scatter
Select
Shape
Shuffle
Slice
SoftMax
TopK
Unary
NVIDIA TensorRT Operators Documentation
»
Search
Please activate JavaScript to enable the search functionality.