TensorRT for RTX 1.3.0
nvinfer1::IRotaryEmbeddingLayer Class Reference

Layer that implements Rotary Position Embedding (RoPE) (https://arxiv.org/abs/2104.09864). More...

#include <NvInfer.h>

Inheritance diagram for nvinfer1::IRotaryEmbeddingLayer:
nvinfer1::ILayer nvinfer1::INoCopy

Public Member Functions

void setInterleaved (bool interleaved) noexcept
 Set whether the input is in interleaved format, i.e., whether the 2-d vectors rotated are taken from adjacent 2 elements in the hidden dimension. The default value is false. More...
 
TRT_NODISCARD bool getInterleaved () const noexcept
 Get whether the input is in interleaved format. The default value is false. More...
 
TRT_NODISCARD bool setRotaryEmbeddingDim (int32_t rotaryEmbeddingDim) noexcept
 Set the number of hidden dimensions participating in RoPE. The default value is 0, representing H, i.e., all hidden dimensions in each head. Must be non-negative and even. More...
 
TRT_NODISCARD int32_t getRotaryEmbeddingDim () const noexcept
 Get the number of hidden dimensions participating in RoPE. The default value is 0, representing H, i.e., all hidden dimensions in each head. More...
 
void setInput (int32_t index, ITensor &tensor) noexcept
 Append or replace an input of this layer with a specific tensor. More...
 
- Public Member Functions inherited from nvinfer1::ILayer
LayerType getType () const noexcept
 Return the type of a layer. More...
 
void setName (char const *name) noexcept
 Set the name of a layer. More...
 
char const * getName () const noexcept
 Return the name of a layer. More...
 
int32_t getNbInputs () const noexcept
 Get the number of inputs of a layer. More...
 
ITensorgetInput (int32_t index) const noexcept
 Get the layer input corresponding to the given index. More...
 
int32_t getNbOutputs () const noexcept
 Get the number of outputs of a layer. More...
 
ITensorgetOutput (int32_t index) const noexcept
 Get the layer output corresponding to the given index. More...
 
void setInput (int32_t index, ITensor &tensor) noexcept
 Replace an input of this layer with a specific tensor. More...
 
TRT_DEPRECATED void setPrecision (DataType dataType) noexcept
 Set the preferred or required computational precision of this layer in a weakly-typed network. More...
 
DataType getPrecision () const noexcept
 get the computational precision of this layer More...
 
TRT_DEPRECATED bool precisionIsSet () const noexcept
 whether the computational precision has been set for this layer More...
 
TRT_DEPRECATED void resetPrecision () noexcept
 reset the computational precision for this layer More...
 
TRT_DEPRECATED void setOutputType (int32_t index, DataType dataType) noexcept
 Set the output type of this layer in a weakly-typed network. More...
 
DataType getOutputType (int32_t index) const noexcept
 get the output type of this layer More...
 
TRT_DEPRECATED bool outputTypeIsSet (int32_t index) const noexcept
 whether the output type has been set for this layer More...
 
TRT_DEPRECATED void resetOutputType (int32_t index) noexcept
 reset the output type for this layer More...
 
void setMetadata (char const *metadata) noexcept
 Set the metadata for this layer. More...
 
char const * getMetadata () const noexcept
 Get the metadata of the layer. More...
 

Protected Member Functions

virtual ~IRotaryEmbeddingLayer () noexcept=default
 
- Protected Member Functions inherited from nvinfer1::ILayer
virtual ~ILayer () noexcept=default
 
- Protected Member Functions inherited from nvinfer1::INoCopy
 INoCopy ()=default
 
virtual ~INoCopy ()=default
 
 INoCopy (INoCopy const &other)=delete
 
INoCopyoperator= (INoCopy const &other)=delete
 
 INoCopy (INoCopy &&other)=delete
 
INoCopyoperator= (INoCopy &&other)=delete
 

Protected Attributes

apiv::VRotaryEmbeddingLayer * mImpl
 
- Protected Attributes inherited from nvinfer1::ILayer
apiv::VLayer * mLayer
 

Detailed Description

Layer that implements Rotary Position Embedding (RoPE) (https://arxiv.org/abs/2104.09864).

Warning
Do not inherit from this class, as doing so will break forward-compatibility of the API and ABI.

Constructor & Destructor Documentation

◆ ~IRotaryEmbeddingLayer()

virtual nvinfer1::IRotaryEmbeddingLayer::~IRotaryEmbeddingLayer ( )
protectedvirtualdefaultnoexcept

Member Function Documentation

◆ getInterleaved()

TRT_NODISCARD bool nvinfer1::IRotaryEmbeddingLayer::getInterleaved ( ) const
inlinenoexcept

Get whether the input is in interleaved format. The default value is false.

See also
setInterleaved

◆ getRotaryEmbeddingDim()

TRT_NODISCARD int32_t nvinfer1::IRotaryEmbeddingLayer::getRotaryEmbeddingDim ( ) const
inlinenoexcept

Get the number of hidden dimensions participating in RoPE. The default value is 0, representing H, i.e., all hidden dimensions in each head.

See also
setRotaryEmbeddingDim

◆ setInput()

void nvinfer1::ILayer::setInput ( int32_t  index,
ITensor tensor 
)
inlinenoexcept

Append or replace an input of this layer with a specific tensor.

Parameters
indexthe index of the input to modify.
tensorthe new input tensor

The indices are as follows:

Input 0 is the input activation tensor. Input 1 is the cosine cache tensor. Input 2 is the sine cache tensor. Input 3 (optional) is the positionIds tensor, which is used for indexing into the cosine and sine caches.

◆ setInterleaved()

void nvinfer1::IRotaryEmbeddingLayer::setInterleaved ( bool  interleaved)
inlinenoexcept

Set whether the input is in interleaved format, i.e., whether the 2-d vectors rotated are taken from adjacent 2 elements in the hidden dimension. The default value is false.

See also
getInterleaved

◆ setRotaryEmbeddingDim()

TRT_NODISCARD bool nvinfer1::IRotaryEmbeddingLayer::setRotaryEmbeddingDim ( int32_t  rotaryEmbeddingDim)
inlinenoexcept

Set the number of hidden dimensions participating in RoPE. The default value is 0, representing H, i.e., all hidden dimensions in each head. Must be non-negative and even.

See also
getRotaryEmbeddingDim

Member Data Documentation

◆ mImpl

apiv::VRotaryEmbeddingLayer* nvinfer1::IRotaryEmbeddingLayer::mImpl
protected

The documentation for this class was generated from the following file:

  Copyright © 2024 NVIDIA Corporation
  Privacy Policy | Manage My Privacy | Do Not Sell or Share My Data | Terms of Service | Accessibility | Corporate Policies | Product Security | Contact