21.02

Commit used by the 21.02 TensorRT NGC container

Changelog

Added

• TensorRT Python API bindings
• TensorRT Python samples
• FP16 support to batchedNMSPlugin #1002
• Configurable input size for TLT MaskRCNN Plugin #986

Changed

• TensorRT version updated to 7.2.2.3
• ONNX-TensorRT v21.02 update
• Polygraphy v0.21.1 update
• PyTorch-Quantization Toolkit v2.1.0 update
  • Documentation update, ONNX opset 13 support, ResNet example
• ONNX-GraphSurgeon v0.28 update
• demoBERT builder updated to work with Tensorflow2 (in compatibility mode)
• Refactor Dockerfiles for OSS container

Removed

• N/A

20.12

Commit used by the 20.12 TensorRT NGC container

Changelog

Added

• Add configurable input size for TLT MaskRCNN Plugin

Changed

• Update symbol export map for plugins
• Correctly use channel dimension when creating Prelu node
• Fix Jetson cross compilation CMakefile

Removed

• N/A

20.11

Commit used by the 20.11 TensorRT NGC container

Changelog

Added

• API documentation for ONNX-GraphSurgeon

Changed

• Support for SM86 in demoBERT
• Updated NGC checkpoint URLs for demoBERT and Tacotron2.

Removed

• N/A

20.10

Commit used by the 20.10 TensorRT NGC container

Changelog

Added

• Polygraphy v0.20.13 - Deep Learning Inference Prototyping and Debugging Toolkit
• PyTorch-Quantization Toolkit v2.0.0
• Updated BERT plugins for variable sequence length inputs
  • Optimized kernels for sequence lengths of 64 and 96 added
• Added Tacotron2 + Waveglow TTS demo #677
• Re-enable GridAnchorRect_TRT plugin with rectangular feature maps #679
• Update batchedNMS plugin to IPluginV2DynamicExt interface #738
• Support 3D inputs in InstanceNormalization plugin #745
• Added this CHANGELOG.md

Changed

• ONNX GraphSurgeon - v0.2.7 with bugfixes, new examples.
• demo/BERT bugfixes for Jetson Xavier
• Updated build Dockerfile to cuda-11.1
• Updated ClangFormat style specification according to TensorRT coding guidelines

Removed

• N/A

TensorRT v7.2.1

TensorRT OSS release corresponding to TensorRT 7.2.1.6 GA build.

Changelog

Added

• Polygraphy v0.20.13 - Deep Learning Inference Prototyping and Debugging Toolkit
• PyTorch-Quantization Toolkit v2.0.0
• Updated BERT plugins for variable sequence length inputs
  • Optimized kernels for sequence lengths of 64 and 96 added
• Added Tacotron2 + Waveglow TTS demo #677
• Re-enable GridAnchorRect_TRT plugin with rectangular feature maps #679
• Update batchedNMS plugin to IPluginV2DynamicExt interface #738
• Support 3D inputs in InstanceNormalization plugin #745
• Added this CHANGELOG.md

Changed

• ONNX GraphSurgeon - v0.2.7 with bugfixes, new examples.
• demo/BERT bugfixes for Jetson Xavier
• Updated build Dockerfile to cuda-11.1
• Updated ClangFormat style specification according to TensorRT coding guidelines

Removed

• N/A

20.09

Commit used by the 20.09 TensorRT NGC container

20.07

Commit used by the 20.07 TensorRT NGC container

20.06

Commit used by the 20.06 TensorRT NGC container

TensorRT v7.1.3

TensorRT plugins, parsers, and samples corresponding to TensorRT 7.1.3.4 Release.

20.04

Commit used by the 20.04 TensorRT NGC container