TensorRT OSS v9.2.0

TensorRT OSS release corresponding to TensorRT 9.2.0.5 release.

Updates since TensorRT 9.1.0 release.

Key Features and Updates:

• trtexec enhancement: Added --weightless flag to mark the engine as weightless.
• Parser changes
  • Added support for Hardmax operator.
  • Changes to a few operator importers to ensure that TensorRT preserves the precision of operations when using strongly typed mode.
• Plugin changes
  • Explicit INT8 support added to bertQKVToContextPlugin.
  • Various bug fixes.
• Updated HuggingFace demo to use transformers v4.31.0 and PyTorch v2.1.0.

TensorRT OSS v9.1.0

TensorRT OSS release corresponding to TensorRT 9.1.0.4 GA release.

Updates since TensorRT 8.6.1 GA release.

Key Features and Updates:

• Update the trt_python_plugin sample.
  • Python plugins API reference is part of the offical TRT Python API.
• Added samples demonstrating the usage of the progress monitor API.
  • Check sampleProgressMonitor for the C++ sample.
  • Check simple_progress_monitor for the Python sample.
• Remove dependencies related to python<3.8 in python samples as we no longer support python<3.8 for python samples.
• Demo changes
  • Added LAMBADA dataset accuracy checks in the HuggingFace demo.
  • Enabled structured sparsity and FP8 quantized batch matrix multiplication(BMM)s in attention in the NeMo demo.
  • Replaced deprecated APIs in the BERT demo.
• Updated tooling
  • Polygraphy v0.49.1

23.08

What's Changed

• Fix python bindings build and README
• Add kNATIVE_INSTANCENORM flag to demoDiffusion
• Update demoDiffusion to support torch 2.x and fix typo in README
• Add HuggingFace Stable Diffusion pipeline demo
• Upgrade pytorch-quantization to 2.1.3

Full Changelog: v8.6.1...23.08

TensorRT OSS v8.6.1

TensorRT OSS release corresponding to TensorRT 8.6.1.6 GA release.

• Updates since TensorRT 8.6.0 EA release.
• Please refer to the TensorRT 8.6.1.6 GA release notes for more information.

Key Features and Updates:

• Added a new flag --use-cuda-graph to demoDiffusion to improve performance.
• Optimized GPT2 and T5 HuggingFace demos to use fp16 I/O tensors for fp16 networks.

TensorRT OSS v8.6.0

TensorRT OSS release corresponding to TensorRT 8.6.0.12 EA release.

• Updates since TensorRT 8.5.3 GA release.
• Please refer to the TensorRT 8.6.0.12 EA release notes for more information.

Key Features and Updates:

• demoDiffusion acceleration is now supported out of the box in TensorRT without requiring plugins.
  • The following plugins have been removed accordingly: GroupNorm, LayerNorm, MultiHeadCrossAttention, MultiHeadFlashAttention, SeqLen2Spatial, and SplitGeLU.
• Added a new sample called onnx_custom_plugin.

We needed to force-push main and release/8.6 branches and v8.6.0 release. If you cloned/pulled the repo recently, please rebase the affected branches. Our apologies for this inconvenience.

TensorRT OSS v8.5.3

TensorRT OSS release corresponding to TensorRT 8.5.3.1 GA release.

• Updates since TensorRT 8.5.2 GA release.
• Please refer to the TensorRT 8.5.3 GA release notes for more information.

Key Features and Updates:

• Added the following HuggingFace demos: GPT-J-6B, GPT2-XL, and GPT2-Medium
• Added nvinfer1::plugin namespace
• Optimized KV Cache performance for T5

TensorRT OSS v8.5.2

TensorRT OSS release corresponding to TensorRT 8.5.2.2 GA release.

Updates since TensorRT 8.5.1 GA release.
Please refer to the TensorRT 8.5.2 GA release notes for more information.

Key Features and Updates:

• Plugin enhancements
  • Added LayerNormPlugin, SplitGeLUPlugin, GroupNormPlugin, and SeqLen2SpatialPlugin to support stable diffusion demo.
• KV-cache and beam search to GPT2 and T5 demos

22.12

Commit used by the 22.12 TensorRT NGC container.

Added

• Stable Diffusion demo using TensorRT Plugins
• KV-cache and beam search to GPT2 and T5 demos
• Perplexity calculation to all HF demos

Changed

• Updated trex to v0.1.5
• Increased default workspace size in demoBERT to build BS=128 fp32 engines
• Use avg_iter=8 and timing cache to make demoBERT perf more stable

Removed

• None

TensorRT OSS v8.5.1

TensorRT OSS release corresponding to TensorRT 8.5.1.7 GA release.

• Updates since TensorRT 8.4.1 GA release.
• Please refer to the TensorRT 8.5.1 GA release notes for more information.

Key Features and Updates:

• Samples enhancements

  • Added sampleNamedDimensions which works with named dimensions.
  • Updated sampleINT8API and introductory_parser_samples to use ONNX models over Caffe/UFF
  • Removed UFF/Caffe samples including sampleMNIST, end_to_end_tensorflow_mnist, sampleINT8, sampleMNISTAPI, sampleUffMNIST, sampleUffPluginV2Ext, engine_refit_mnist, int8_caffe_mnist, uff_custom_plugin, sampleFasterRCNN, sampleUffFasterRCNN, sampleGoogleNet, sampleSSD, sampleUffSSD, sampleUffMaskRCNN and uff_ssd.

• Plugin enhancements

  • Added GridAnchorRectPlugin to support rectangular feature maps in gridAnchorPlugin.
  • Added ROIAlignPlugin to support the ONNX operator RoiAlign. The ONNX parser will automatically route ROIAlign ops through the plugin.
  • Added Hopper support for the BERTQKVToContextPlugin plugin.
  • Exposed the use_int8_scale_max attribute in the BERTQKVToContextPlugin plugin to allow users to disable the by-default usage of INT8 scale factors to optimize softmax MAX reduction in versions 2 and 3 of the plugin.

• ONNX-TensorRT changes

  • Added support for operator Reciprocal.

• Build containers

  • Updated default cuda versions to 11.8.0.

• Tooling enhancements

  • Updated onnx-graphsurgeon to v0.3.25.
  • Updated Polygraphy to v0.43.1.
  • Updated polygraphy-extension-trtexec to v0.0.8.
  • Updated Tensorflow Quantization Toolkit to v0.2.0.

TensorRT OSS v8.4.3

TensorRT OSS release corresponding to TensorRT 8.4.3.1 release.

• Updates since TensorRT 8.4.2 release.
• Please refer to the TensorRT 8.4.3 release notes for more information.

Key Updates:

• Python packages for Python 3.10.
• Bug fix for potential overlaps in H2D and inference execution in trtexec.