21.06

Commit used by the 21.06 TensorRT NGC container

Changelog

Added

• Add switch for batch-agnostic mode in NMS plugin
• Add missing model.py in uff_custom_plugin sample

Changed

• Update to Polygraphy v0.29.2
• Update to ONNX-GraphSurgeon v0.3.9
• Fix numerical errors for float type in NMS/batchedNMS plugins
• Update demoBERT input dimensions to match Triton requirement #1051
• Optimize TLT MaskRCNN plugins:
  • enable fp16 precision in multilevelCropAndResizePlugin and multilevelProposeROIPlugin
  • Algorithms optimization for NMS kernels and ROIAlign kernel
  • Fix invalid cuda config issue when bs is larger than 32
  • Fix issues found on Jetson NANO

Removed

• Removed fcplugin from demoBERT to improve inference latency on GA100/Turing

21.05

Commit used by the 21.05 TensorRT NGC container

Changelog

Added

• Extended support for ONNX operator InstanceNormalization to 5D tensors
• Support negative indices in ONNX Gather operator
• Add support for importing ONNX double-typed weights as float
• ONNX-GraphSurgeon (v0.3.7) support for models with externally stored weights

Changed

• Update ONNX-TensorRT to 21.05
• Relicense ONNX-TensorRT under Apache2
• demoBERT builder fixes for multi-batch
• Speedup demoBERT build using global timing cache and disable cuDNN tactics
• Standardize python package versions across OSS samples
• Bugfixes in multilevelProposeROI and bertQKV plugin
• Fix memleaks in samples logger

21.04

Commit used by the 21.04 TensorRT NGC container

Changelog

Added

• SM86 kernels for BERT MHA plugin
• Added opset13 support for SoftMax, LogSoftmax, Squeeze, and Unsqueeze.
• Added support for the EyeLike and GatherElements operators.

Changed

• Updated TensorRT version to v7.2.3.4.
• Update to ONNX-TensorRT 21.03
• ONNX-GraphSurgeon (v0.3.4) - updates fold_constants to correctly exit early.
• Set default CUDA_INSTALL_DIR #798
• Plugin bugfixes, qkv kernels for sm86
• Fixed GroupNorm CMakeFile for cu sources #1083
• Permit groupadd with non-unique GID in build containers #1091
• Avoid reinterpret_cast #146
• Clang-format plugins and samples
• Avoid arithmetic on void pointer in multilevelProposeROIPlugin.cpp #1028
• Update BERT plugin documentation.

Removed

• Removes extra terminate call in InstanceNorm

21.03

Commit used by the 21.03 TensorRT NGC container

Changelog

Added

• Optimized FP16 NMS/batchedNMS plugins with n-bit radix sort and based on IPluginV2DynamicExt
• ProposalDynamic and CropAndResizeDynamic plugins based on IPluginV2DynamicExt

Changed

• ONNX-TensorRT v21.03 update
• ONNX-GraphSurgeon v0.3.3 update
• Bugfix for scaledSoftmax kernel #1096

Removed

• N/A

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