## 10.13.2 GA - 2025-8-18 For more information, see the [10.13.2 release notes.](https://docs.nvidia.com/deeplearning/tensorrt/10.13.2/getting-started/release-notes.html) - Added support for CUDA 13.0, dropped support for CUDA 11.X - Dropped support for Ubuntu 20.04 - Dropped support for Python versions < 3.10 for samples and demos

## 10.12.0 GA - 2025-6-10 Key Features and Updates: - Plugin changes - Migrated `IPluginV2`-descendent version 1 of `cropAndResizeDynamic`, to version 2, which implements `IPluginV3`. - Note: The newer versions preserve the attributes and I/O of the corresponding older plugin version. The older plugin versions are deprecated and will be removed in a future release - Deprecated the listed versions of the following plugins: - `DecodeBbox3DPlugin` (version 1) - `DetectionLayer_TRT` (version 1) - `EfficientNMS_TRT` (version 1) - `FlattenConcat_TRT` (version 1) - `GenerateDetection_TRT` (version 1) - `GridAnchor_TRT` (version 1) - `GroupNormalizationPlugin` (version 1) - `InstanceNormalization_TRT` (version 2) - `ModulatedDeformConv2d` (version 1) - `MultilevelCropAndResize_TRT` (version 1) - `MultilevelProposeROI_TRT` (version 1) - `RPROI_TRT` (version 1) - `PillarScatterPlugin` (version 1) - `PriorBox_TRT` (version 1) - `ProposalLayer_TRT` (version 1) - `ProposalDynamic` (version 1) - `Region_TRT` (version 1) - `Reorg_TRT` (version 2) - `ResizeNearest_TRT` (version 1) - `ScatterND` (version 1) - `VoxelGeneratorPlugin` (version 1) - Demo changes - Added [Image-to-Image](demo/Diffusion#generate-an-image-with-stable-diffusion-v35-large-with-controlnet-guided-by-an-image-and-a-text-prompt) support for Stable Diffusion v3.5-large ControlNet models. - Enabled download of [pre-exported ONNX models](https://huggingface.co/stabilityai/stable-diffusion-3.5-large-tensorrt) for the Stable Diffusion v3.5-large pipeline. - Sample changes - Added two refactored python samples [1_run_onnx_with_tensorrt](samples/python/refactored/1_run_onnx_with_tensorrt) and [2_construct_network_with_layer_apis](samples/python/refactored/2_construct_network_with_layer_apis) - Parser changes - Added support for integer-typed base tensors for `Pow` operations - Added support for custom `MXFP8` quantization operations - Added support for ellipses, diagonal, and broadcasting in `Einsum` operations

## 10.11.0 GA - 2025-5-21 Key Features and Updates: - Plugin changes - Migrated `IPluginV2`-descendent version 1 of `modulatedDeformConvPlugin`, to version 2, which implements `IPluginV3`. - Migrated `IPluginV2`-descendent version 1 of `DisentangledAttention_TRT`, to version 2, which implements `IPluginV3`. - Migrated `IPluginV2`-descendent version 1 of `MultiscaleDeformableAttnPlugin_TRT`, to version 2, which implements `IPluginV3`. - Note: The newer versions preserve the attributes and I/O of the corresponding older plugin version. The older plugin versions are deprecated and will be removed in a future release. - Demo changes - demoDiffusion - Added support for Stable Diffusion 3.5-medium and 3.5-large pipelines in BF16 and FP16 precisions. - Parser changes - Added `kENABLE_UINT8_AND_ASYMMETRIC_QUANTIZATION_DLA` parser flag to enable UINT8 asymmetric quantization on engines targeting DLA. - Removed restriction that inputs to `RandomNormalLike` and `RandomUniformLike` must be tensors. - Clarified limitations of scan outputs for `Loop` nodes.

# 10.10.0 GA For more information, see the [TensorRT 10.10.0 release notes](https://docs.nvidia.com/deeplearning/tensorrt/latest/getting-started/release-notes.html#tensorrt-10-10-0). Key Features and Updates: - Demo changes - demoDiffusion - Added fp16 and fp8 LoRA support for demo diffusion’s SDXL and FLUX pipeline. - Added fp16 ControlNet support for demo diffusion’s SDXL pipeline. - Plugin changes - Deprecated the enum classes [PluginVersion](https://docs.nvidia.com/deeplearning/tensorrt/latest/_static/c-api/namespacenvinfer1.html#a6fb3932a2896d82a94c8783e640afb34) & [PluginCreatorVersion](https://docs.nvidia.com/deeplearning/tensorrt/latest/_static/c-api/namespacenvinfer1.html#a43c4159a19c23f74234f3c34124ea0c5). PluginVersion & PluginCreatorVersion are used only in relation to IPluginV2-descendent plugin interfaces, which are all deprecated. - Added the following APIs that enable users to obtain a list of all Plugin Creators hierarchically registered to a TensorRT Plugin Registry ([C++](https://docs.nvidia.com/deeplearning/tensorrt/latest/_static/c-api/classnvinfer1_1_1_i_plugin_registry.html), [Python](https://docs.nvidia.com/deeplearning/tensorrt/latest/_static/python-api/infer/Plugin/IPluginRegistry.html)) instance. - C++ API: IPluginRegistry::getAllCreatorsRecursive() - Python API: IPluginRegistry.all_creators_recursive - Parser changes - Cleaned up log spam when the ONNX network contained a mixture Plugins and LocalFunctions - UINT8 constants are now properly imported for QuantizeLinear & DequantizeLinear nodes - Plugin fallback importer now also reads its namespace from a Node's domain field - Sample changes - Added support for the [python_plugin sample](https://github.com/NVIDIA/TensorRT/tree/release/10.9/samples/python/python_plugin) to compile targets to Blackwell.

# 10.9.0 GA For more information, see the [TensorRT 10.9.0 release notes](https://docs.nvidia.com/deeplearning/tensorrt/latest/getting-started/release-notes.html#tensorrt-10-9-0). Key Features and Updates: - Demo changes - demoDiffusion - Added Canny ControlNet support for the SDXL pipeline - Plugin changes - Added a readme to the GroupNormalization plugin (`GroupNormalizationPlugin`) - [4314](https://github.com/NVIDIA/TensorRT/issues/4314) - Fixed bug in `CustomQKVToConte mxtPluginDynamic` version 3 where SM 100 was not considered a supported platform. - Parser changes - Added support for Python AOT plugins - Added support for opset 21 GroupNorm - [4336](https://github.com/NVIDIA/TensorRT/issues/4336) - Fixed support for opset 18+ ScatterND - Sample changes - Added a new sample `dds_faster_rcnn` which demonstrates how to handle data-dependent shaped outputs with `IOutputAllocator`. - Fixed issues: - Fixed streamReaderV2 Python API performance issue - [4327](https://github.com/NVIDIA/TensorRT/issues/4327)

# 10.8.0 GA For more information, see the [TensorRT 10.8.0 release notes](https://docs.nvidia.com/deeplearning/tensorrt/release-notes/index.html#rel-10-8-0). Key Features and Updates: - Demo changes - demoDiffusion - Added [Image-to-Image](demo/Diffusion#generate-an-image-guided-by-an-initial-image-and-a-text-prompt-using-flux) support for Flux-1.dev and Flux.1-schnell pipelines. - Added [ControlNet](demo/Diffusion#generate-an-image-guided-by-a-text-prompt-and-a-control-image-using-flux-controlnet) support for [FLUX.1-Canny-dev](https://huggingface.co/black-forest-labs/FLUX.1-Canny-dev) and [FLUX.1-Depth-dev](https://huggingface.co/black-forest-labs/FLUX.1-Depth-dev) pipelines. Native FP8 quantization is also supported for these pipelines. - Added support for ONNX model export only mode. See [--onnx-export-only](demo/Diffusion#https://gitlab-master.nvidia.com/TensorRT/Public/oss/-/tree/release/10.8/demo/Diffusion?ref_type=heads#use-separate-directories-for-individual-onnx-models). - Added FP16, BF16, FP8, and FP4 support for all Flux Pipelines. - Plugin changes - Added SM 100 and SM 120 support to bertQKVToContextPlugin. This enables demo/BERT on Blackwell GPUs. - Sample changes - Added a new `sampleEditableTimingCache` to demonstrate how to build an engine with the desired tactics by modifying the timing cache. - Deleted the `sampleAlgorithmSelector` sample. - Fixed `sampleOnnxMNIST` by updating the correct INT8 dynamic range. - Parser changes - Added support for `FLOAT4E2M1` types for quantized networks. - Added support for dynamic axes and improved performance of `CumSum` operations. - Fixed the import of local functions when their input tensor names aliased one from an outside scope. - Added support for `Pow` ops with integer-typed exponent values. - Fixed issues - Fixed segmentation of boolean constant nodes - [4224](https://github.com/NVIDIA/TensorRT/issues/4224). - Fixed accuracy issue when multiple optimization profiles were defined [4250](https://github.com/NVIDIA/TensorRT/issues/4250).

# 10.7.0 GA For more information, see the [TensorRT 10.7.0 release notes](https://docs.nvidia.com/deeplearning/tensorrt/release-notes/index.html#rel-10-7-0). Key Feature and Updates: - Demo Changes - demoDiffusion - Enabled low-vram for the Flux pipeline. Users can now run the pipelines on systems with 32GB VRAM. - Added support for [FLUX.1-schnell](https://huggingface.co/black-forest-labs/FLUX.1-schnell) pipeline. - Enabled weight streaming mode for Flux pipeline. - Plugin Changes - On Blackwell and later platforms, TensorRT will drop cuDNN support on the following categories of plugins - User-written `IPluginV2Ext`, `IPluginV2DynamicExt`, and `IPluginV2IOExt` plugins that are dependent on cuDNN handles provided by TensorRT (via the `attachToContext()` API). - TensorRT standard plugins that use cuDNN, specifically: - `InstanceNormalization_TRT` (version: 1, 2, and 3) present in `plugin/instanceNormalizationPlugin/`. - `GroupNormalizationPlugin` (version: 1) present in `plugin/groupNormalizationPlugin/`. - Note: These normalization plugins are superseded by TensorRT’s native `INormalizationLayer` ([C++](https://docs.nvidia.com/deeplearning/tensorrt/api/c_api/classnvinfer1_1_1_i_normalization_layer.html), [Python](https://docs.nvidia.com/deeplearning/tensorrt/operators/docs/Normalization.html)). TensorRT support for cuDNN-dependent plugins remain unchanged on pre-Blackwell platforms. - Parser Changes - Now prioritizes using plugins over local functions when a corresponding plugin is available in the registry. - Added dynamic axes support for `Squeeze` and `Unsqueeze` operations. - Added support for parsing mixed-precision `BatchNormalization` nodes in strongly-typed mode. - Addressed Issues - Fixed [4113](https://github.com/NVIDIA/TensorRT/issues/4113).

## 10.6.0 GA For more information, see the [TensorRT 10.6.0 release notes](https://docs.nvidia.com/deeplearning/tensorrt/release-notes/index.html#rel-10-6-0). Key Feature and Updates: - Demo Changes - demoBERT: The use of `fcPlugin` in demoBERT has been removed. - demoBERT: All TensorRT plugins now used in demoBERT (`CustomEmbLayerNormDynamic`, `CustomSkipLayerNormDynamic`, and `CustomQKVToContextDynamic`) now have versions that inherit from IPluginV3 interface classes. The user can opt-in to use these V3 plugins by specifying `--use-v3-plugins` to the builder scripts. - Opting-in to use V3 plugins does not affect performance, I/O, or plugin attributes. - There is a known issue in the V3 (version 4) of `CustomQKVToContextDynamic` plugin from TensorRT 10.6.0, causing an internal assertion error if either the batch or sequence dimensions differ at runtime from the ones used to serialize the engine. See the “known issues” section of the [TensorRT-10.6.0 release notes](https://docs.nvidia.com/deeplearning/tensorrt/release-notes/index.html#rel-10-6-0). - For smoother migration, the default behavior is still using the deprecated `IPluginV2DynamicExt`-derived plugins, when the flag: `--use-v3-plugins` isn't specified in the builder scripts. The flag `--use-deprecated-plugins` was added as an explicit way to enforce the default behavior, and is mutually exclusive with `--use-v3-plugins`. - demoDiffusion - Introduced BF16 and FP8 support for the [Flux.1-dev](demo/Diffusion#generate-an-image-guided-by-a-text-prompt-using-flux) pipeline. - Expanded FP8 support on Ada platforms. - Enabled LoRA adapter compatibility for SDv1.5, SDv2.1, and SDXL pipelines using Diffusers version 0.30.3. - Sample Changes - Added the Python sample [quickly_deployable_plugins](samples/python/quickly_deployable_plugins), which demonstrates quickly deployable Python-based plugin definitions (QDPs) in TensorRT. QDPs are a simple and intuitive decorator-based approach to defining TensorRT plugins, requiring drastically less code. - Plugin Changes - The `fcPlugin` has been deprecated. Its functionality has been superseded by the [IMatrixMultiplyLayer](https://docs.nvidia.com/deeplearning/tensorrt/api/c_api/classnvinfer1_1_1_i_matrix_multiply_layer.html) that is natively provided by TensorRT. - Migrated `IPluginV2`-descendent version 1 of `CustomEmbLayerNormDynamic`, to version 6, which implements `IPluginV3`. - The newer versions preserve the attributes and I/O of the corresponding older plugin version. - The older plugin versions are deprecated and will be removed in a future release. - Parser Changes - Updated ONNX submodule version to 1.17.0. - Fixed issue where conditional layers were incorrectly being added. - Updated local function metadata to contain more information. - Added support for parsing nodes with Quickly Deployable Plugins. - Fixed handling of optional outputs. - Tool Updates - ONNX-Graphsurgeon updated to version 0.5.3 - Polygraphy updated to 0.49.14.