@@ -1,19 +1,64 @@
 # TensorRT OSS Release Changelog
 
+## [8.0.1](https://docs.nvidia.com/deeplearning/tensorrt/release-notes/tensorrt-8.html#tensorrt-8) - 2021-07-02
+### Added
+- Added support for the following ONNX operators: `Celu`, `CumSum`, `EyeLike`, `GatherElements`, `GlobalLpPool`, `GreaterOrEqual`, `LessOrEqual`, `LpNormalization`, `LpPool`, `ReverseSequence`, and `SoftmaxCrossEntropyLoss` [details](). 
+- Rehauled `Resize` ONNX operator, now fully supporting the following modes:
+  - Coordinate Transformation modes: `half_pixel`, `pytorch_half_pixel`, `tf_half_pixel_for_nn`, `asymmetric`, and `align_corners`.
+  - Modes: `nearest`, `linear`.
+  - Nearest Modes: `floor`, `ceil`, `round_prefer_floor`, `round_prefer_ceil`.
+- Added support for multi-input ONNX `ConvTranpose` operator.
+- Added support for 3D spatial dimensions in ONNX `InstanceNormalization`.
+- Added support for generic 2D padding in ONNX.
+- ONNX `QuantizeLinear` and `DequantizeLinear` operators leverage `IQuantizeLayer` and `IDequantizeLayer`.
+  - Added support for tensor scales.
+  - Added support for per-axis quantization.
+- Added `EfficientNMS_TRT`, `EfficientNMS_ONNX_TRT` plugins and experimental support for ONNX `NonMaxSuppression` operator.
+- Added `ScatterND` plugin.
+- Added TensorRT [QuickStart Guide](https://github.com/NVIDIA/TensorRT/tree/master/quickstart).
+- Added new samples: [engine_refit_onnx_bidaf](https://docs.nvidia.com/deeplearning/tensorrt/sample-support-guide/index.html#engine_refit_onnx_bidaf) builds an engine from ONNX BiDAF model and refits engine with new weights, [efficientdet](samples/python/efficientdet) and [efficientnet](samples/python/efficientnet) samples for demonstrating Object Detection using TensorRT.
+- Added support for Ubuntu20.04 and RedHat/CentOS 8.3.
+- Added Python 3.9 support.
+
+### Changed
+- Update Polygraphy to [v0.30.3](tools/Polygraphy/CHANGELOG.md#v0303-2021-06-25).
+- Update ONNX-GraphSurgeon to [v0.3.10](tools/onnx-graphsurgeon/CHANGELOG.md#v0310-2021-05-20).
+- Update Pytorch Quantization toolkit to v2.1.0.
+- Notable TensorRT API updates
+  - TensorRT now declares API’s with the `noexcept` keyword. All TensorRT classes that an application inherits from (such as IPluginV2) must guarantee that methods called by TensorRT do not throw uncaught exceptions, or the behavior is undefined.
+  - Destructors for classes with `destroy()` methods were previously protected. They are now public, enabling use of smart pointers for these classes. The `destroy()` methods are deprecated.
+- Moved `RefitMap` API from ONNX parser to core TensorRT.
+- Various bugfixes for plugins, samples and ONNX parser.
+- Port demoBERT to tensorflow2 and update UFF samples to leverage nvidia-tensorflow1 container.
+
+### Removed
+- `IPlugin` and `IPluginFactory` interfaces were deprecated in TensorRT 6.0 and have been removed in TensorRT 8.0. We recommend that you write new plugins or refactor existing ones to target the `IPluginV2DynamicExt` and `IPluginV2IOExt` interfaces. For more information, refer to [Migrating Plugins From TensorRT 6.x Or 7.x To TensorRT 8.x.x](https://docs.nvidia.com/deeplearning/tensorrt/developer-guide/index.html#migrating-plugins-6x-7x-to-8x).
+  - For plugins based on `IPluginV2DynamicExt` and `IPluginV2IOExt`, certain methods with legacy function signatures (derived from `IPluginV2` and `IPluginV2Ext` base classes) which were deprecated and marked for removal in TensorRT 8.0 will no longer be available.
+- Removed `samplePlugin` since it showcased IPluginExt interface, which is no longer supported in TensorRT 8.0.
+- Removed `sampleMovieLens` and `sampleMovieLensMPS`.
+- Removed Dockerfile for Ubuntu 16.04. TensorRT 8.0 debians for Ubuntu 16.04 require python 3.5 while minimum required python version for TensorRT OSS is 3.6.
+- Removed support for PowerPC builds, consistent with TensorRT GA releases.
+
+### Notes
+- We had deprecated the Caffe Parser and UFF Parser in TensorRT 7.0. They are still tested and functional in TensorRT 8.0, however, we plan to remove the support in a future release. Ensure you migrate your workflow to use `tf2onnx`, `keras2onnx` or [TensorFlow-TensorRT (TF-TRT)](https://docs.nvidia.com/deeplearning/frameworks/tf-trt-user-guide/index.html).
+- Refer to [TensorRT 8.0.1 GA Release Notes](https://docs.nvidia.com/deeplearning/tensorrt/archives/tensorrt-801/release-notes/tensorrt-8.html#rel_8-0-1) for additional details
+
+
 ## [21.06](https://github.com/NVIDIA/TensorRT/releases/tag/21.06) - 2021-06-23
+### 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](tools/Polygraphy/CHANGELOG.md#v0292-2021-04-30)
 - Update to [ONNX-GraphSurgeon v0.3.9](tools/onnx-graphsurgeon/CHANGELOG.md#v039-2021-04-20)
-- Add missing model.py in `uff_custom_plugin` sample
 - Fix numerical errors for float type in NMS/batchedNMS plugins
 - Update demoBERT input dimensions to match Triton requirement [#1051](https://github.com/NVIDIA/TensorRT/pull/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
-- Add switch for batch-agnostic mode in NMS plugin
 
 ### Removed
 - Removed fcplugin from demoBERT to improve latency
 
@@ -80,8 +80,8 @@ endif()
 ############################################################################################
 # Dependencies
 
-set(DEFAULT_CUDA_VERSION 11.1)
-set(DEFAULT_CUDNN_VERSION 8.0)
+set(DEFAULT_CUDA_VERSION 11.3.1)
+set(DEFAULT_CUDNN_VERSION 8.2)
 set(DEFAULT_PROTOBUF_VERSION 3.0.0)
 set(DEFAULT_CUB_VERSION 1.8.0)
 
 
@@ -15,16 +15,16 @@ This repository contains the Open Source Software (OSS) components of NVIDIA Ten
 To build the TensorRT-OSS components, you will first need the following software packages.
 
 **TensorRT GA build**
-* [TensorRT](https://developer.nvidia.com/nvidia-tensorrt-download) v7.2.3.4
+* [TensorRT](https://developer.nvidia.com/nvidia-tensorrt-download) v8.0.1.6
 
 **System Packages**
 * [CUDA](https://developer.nvidia.com/cuda-toolkit)
   * Recommended versions:
-  * cuda-11.x + cuDNN-8.1
-  * cuda-10.2 + cuDNN-8.1
+  * cuda-11.3.1 + cuDNN-8.2
+  * cuda-10.2 + cuDNN-8.2
 * [GNU make](https://ftp.gnu.org/gnu/make/) >= v4.1
 * [cmake](https://github.com/Kitware/CMake/releases) >= v3.13
-* [python](<https://www.python.org/downloads/>) >= v3.6.5
+* [python](<https://www.python.org/downloads/>) >= v3.6.9
 * [pip](https://pypi.org/project/pip/#history) >= v19.0
 * Essential utilities
   * [git](https://git-scm.com/downloads), [pkg-config](https://www.freedesktop.org/wiki/Software/pkg-config/), [wget](https://www.gnu.org/software/wget/faq.html#download), [zlib](https://zlib.net/)
@@ -34,16 +34,16 @@ To build the TensorRT-OSS components, you will first need the following software
   * [Docker](https://docs.docker.com/install/) >= 19.03
   * [NVIDIA Container Toolkit](https://github.com/NVIDIA/nvidia-docker)
 * Toolchains and SDKs
-  * (Cross compilation for Jetson platform) [NVIDIA JetPack](https://developer.nvidia.com/embedded/jetpack) >= 4.4
+  * (Cross compilation for Jetson platform) [NVIDIA JetPack](https://developer.nvidia.com/embedded/jetpack) >= 4.6 (July 2021)
   * (For Windows builds) [Visual Studio](https://visualstudio.microsoft.com/vs/older-downloads/) 2017 Community or Enterprise edition
   * (Cross compilation for QNX platform) [QNX Toolchain](https://blackberry.qnx.com/en)
 * PyPI packages (for demo applications/tests)
-  * [onnx](https://pypi.org/project/onnx/1.7.0/) 1.7.0
-  * [onnxruntime](https://pypi.org/project/onnxruntime/1.6.0/) >= 1.6.0
-  * [tensorflow-gpu](https://pypi.org/project/tensorflow/2.2.2/) >= 2.2.2
-  * [Pillow](https://pypi.org/project/Pillow/8.1.2/) >= 8.1.2
-  * [pycuda](https://pypi.org/project/pycuda/)
-  * [numpy](https://pypi.org/project/numpy/)
+  * [onnx](https://pypi.org/project/onnx/) 1.8.0
+  * [onnxruntime](https://pypi.org/project/onnxruntime/) 1.7.0
+  * [tensorflow-gpu](https://pypi.org/project/tensorflow/) >= 2.4.1
+  * [Pillow](https://pypi.org/project/Pillow/) >= 8.1.2
+  * [pycuda](https://pypi.org/project/pycuda/) < 2020.1
+  * [numpy](https://pypi.org/project/numpy/) 1.21.0
   * [pytest](https://pypi.org/project/pytest/)
 * Code formatting tools (for contributors)
   * [Clang-format](https://clang.llvm.org/docs/ClangFormat.html)
@@ -54,89 +54,78 @@ To build the TensorRT-OSS components, you will first need the following software
 ## Downloading TensorRT Build
 
 1. #### Download TensorRT OSS
-	**On Linux: Bash**
 	```bash
 	git clone -b master https://github.com/nvidia/TensorRT TensorRT
 	cd TensorRT
 	git submodule update --init --recursive
 	```
-	**On Windows: Powershell**
-	```powershell
-	git clone -b master https://github.com/nvidia/TensorRT TensorRT
-	cd TensorRT
-	git submodule update --init --recursive
-	```
 
-2. #### Specify the TensorRT Release build
+2. #### (Optional - if not using TensorRT container) Specify the TensorRT GA release build
 
-    If using NVIDIA build containers, TensorRT is preinstalled under `/usr/lib/x86_64-linux-gnu`.
+    If using the TensorRT OSS build container, TensorRT libraries are preinstalled under `/usr/lib/x86_64-linux-gnu` and you may skip this step.
 
-    Else download and extract the TensorRT build from [NVIDIA Developer Zone](https://developer.nvidia.com/nvidia-tensorrt-download).
+    Else download and extract the TensorRT GA build from [NVIDIA Developer Zone](https://developer.nvidia.com/nvidia-tensorrt-download).
 
-    **Example: Ubuntu 18.04 on x86-64 with cuda-11.1**
+    **Example: Ubuntu 18.04 on x86-64 with cuda-11.3**
 
     ```bash
     cd ~/Downloads
-    tar -xvzf TensorRT-7.2.3.4.Ubuntu-18.04.x86_64-gnu.cuda-11.1.cudnn8.1.tar.gz
-    export TRT_LIBPATH=`pwd`/TensorRT-7.2.3.4
+    tar -xvzf TensorRT-8.0.1.6.Ubuntu-18.04.x86_64-gnu.cuda-11.3.cudnn8.2.tar.gz
+    export TRT_LIBPATH=`pwd`/TensorRT-8.0.1.6
     ```
 
-    **Example: Windows on x86-64 with cuda-11.0**
+    **Example: Windows on x86-64 with cuda-11.3**
 
     ```powershell
     cd ~\Downloads
-    Expand-Archive .\TensorRT-7.2.3.4.Windows10.x86_64.cuda-11.0.cudnn8.1.zip
-    $Env:TRT_LIBPATH = '$(Get-Location)\TensorRT-7.2.3.4'
+    Expand-Archive .\TensorRT-8.0.1.6.Windows10.x86_64.cuda-11.3.cudnn8.2.zip
+    $Env:TRT_LIBPATH = '$(Get-Location)\TensorRT-8.0.1.6'
     $Env:PATH += 'C:\Program Files (x86)\Microsoft Visual Studio\2017\Professional\MSBuild\15.0\Bin\'
     ```
 
 
-3. #### (Optional) JetPack SDK for Jetson builds
-    Using the JetPack SDK manager, download the host components. Steps:
-    1. Download and launch the SDK manager. Login with your developer account.
+3. #### (Optional - for Jetson builds only) Download the JetPack SDK
+    1. Download and launch the JetPack SDK manager. Login with your NVIDIA developer account.
     2. Select the  platform and target OS  (example: Jetson AGX Xavier, `Linux Jetpack 4.4`), and click Continue.
     3. Under `Download & Install Options` change the download folder and select `Download now, Install later`. Agree to the license terms and click Continue.
     4. Move the extracted files into the `<TensorRT-OSS>/docker/jetpack_files` folder.
 
 
 ## Setting Up The Build Environment
 
-For native builds, install the [prerequisite](#prerequisites) *System Packages*. Alternatively (recommended for non-Windows builds), install Docker and generate a build container as described below:
+For Linux platforms, we recommend that you generate a docker container for building TensorRT OSS as described below. For native builds, on Windows for example, please install the [prerequisite](#prerequisites) *System Packages*.
 
 1. #### Generate the TensorRT-OSS build container.
-    The TensorRT-OSS build container can be generated using the Dockerfiles and build script included with TensorRT-OSS. The build container is bundled with packages and environment required for building TensorRT OSS.
+    The TensorRT-OSS build container can be generated using the supplied Dockerfiles and build script. The build container is configured for building TensorRT OSS out-of-the-box.
 
-    **Example: Ubuntu 18.04 on x86-64 with cuda-11.1**
-    ```bash
-    ./docker/build.sh --file docker/ubuntu-18.04.Dockerfile --tag tensorrt-ubuntu-1804 --cuda 11.1
-    ```
-    **Example: Ubuntu 18.04 cross-compile for PowerPC with cuda-11.0**
+    **Example: Ubuntu 18.04 on x86-64 with cuda-11.3**
     ```bash
-    ./docker/build.sh --file docker/ubuntu-cross-ppc64le.Dockerfile --tag tensorrt-ubuntu-ppc --cuda 11.0
+    ./docker/build.sh --file docker/ubuntu-18.04.Dockerfile --tag tensorrt-ubuntu18.04-cuda11.3 --cuda 11.3.1
     ```
-    **Example: CentOS/RedHat 7 on x86-64 with cuda-11.0**
+    **Example: CentOS/RedHat 8 on x86-64 with cuda-10.2**
     ```bash
-    ./docker/build.sh --file docker/centos-7.Dockerfile --tag tensorrt-centos --cuda 11.0
+    ./docker/build.sh --file docker/centos-8.Dockerfile --tag tensorrt-centos8-cuda10.2 --cuda 10.2
     ```
-    **Example: Ubuntu 18.04 cross-compile for Jetson (arm64) with cuda-10.2 (JetPack SDK)**
+    **Example: Ubuntu 18.04 cross-compile for Jetson (aarch64) with cuda-10.2 (JetPack SDK)**
     ```bash
-    ./docker/build.sh --file docker/ubuntu-cross-aarch64.Dockerfile --tag tensorrt-cross-jetpack --cuda 10.2
+    ./docker/build.sh --file docker/ubuntu-cross-aarch64.Dockerfile --tag tensorrt-jetpack-cuda10.2 --cuda 10.2
     ```
 
 2. #### Launch the TensorRT-OSS build container.
     **Example: Ubuntu 18.04 build container**
 	```bash
-	./docker/launch.sh --tag tensorrt-ubuntu-1804 --gpus all
+	./docker/launch.sh --tag tensorrt-ubuntu18.04-cuda11.3 --gpus all
 	```
 	> NOTE:
-	1. Use the tag corresponding to the build container.
-	2. To run TensorRT/CUDA programs in the build container, install [NVIDIA Container Toolkit](#prerequisites). Docker versions < 19.03 require `nvidia-docker2` and `--runtime=nvidia` flag for docker run commands. On versions >= 19.03, you need the `nvidia-container-toolkit` package and `--gpus all` flag.
-	3. sudo password for Ubuntu containers is 'nvidia'.
+	1. Use the `--tag` corresponding to build container generated in Step 1.
+	2. [NVIDIA Container Toolkit](#prerequisites) is required for GPU access (running TensorRT applications) inside the build container.
+	3. `sudo` password for Ubuntu build containers is 'nvidia'.
+	4. Specify port number using `--jupyter <port>` for launching Jupyter notebooks.
 
 ## Building TensorRT-OSS
 * Generate Makefiles or VS project (Windows) and build.
 
-   **Example: Linux (x86-64) build with default cuda-11.1**
+   **Example: Linux (x86-64) build with default cuda-11.3**
 	```bash
 	cd $TRT_OSSPATH
 	mkdir -p build && cd build
@@ -157,13 +146,6 @@ For native builds, install the [prerequisite](#prerequisites) *System Packages*.
 	cmake .. -DTRT_LIB_DIR=$TRT_LIBPATH -DTRT_OUT_DIR=`pwd`/out -DCMAKE_TOOLCHAIN_FILE=$TRT_OSSPATH/cmake/toolchains/cmake_aarch64.toolchain -DCUDA_VERSION=10.2
 	make -j$(nproc)
 	```
-    **Example: Cross-Compile for QNX with cuda-10.2**
-	```bash
-	cd $TRT_OSSPATH
-	mkdir -p build && cd build
-	cmake .. -DTRT_LIB_DIR=$TRT_LIBPATH -DTRT_OUT_DIR=`pwd`/out -DCMAKE_TOOLCHAIN_FILE=$TRT_OSSPATH/cmake/toolchains/cmake_qnx.toolchain -DCUDA_VERSION=10.2
-	make -j$(nproc)
-	```
     **Example: Windows (x86-64) build in Powershell**
 	```powershell
 	cd $Env:TRT_OSSPATH
@@ -172,16 +154,15 @@ For native builds, install the [prerequisite](#prerequisites) *System Packages*.
 	msbuild ALL_BUILD.vcxproj
 	```
 	> NOTE:
-	1. The default CUDA version used by CMake is 11.1. To override this, for example to 10.2, append `-DCUDA_VERSION=10.2` to the cmake command.
-	2. If samples fail to link on CentOS7, create this symbolic link: `ln -s $TRT_OUT_DIR/libnvinfer_plugin.so $TRT_OUT_DIR/libnvinfer_plugin.so.7`
+	1. The default CUDA version used by CMake is 11.3.1. To override this, for example to 10.2, append `-DCUDA_VERSION=10.2` to the cmake command.
+	2. If samples fail to link on CentOS7, create this symbolic link: `ln -s $TRT_OUT_DIR/libnvinfer_plugin.so $TRT_OUT_DIR/libnvinfer_plugin.so.8`
 * Required CMake build arguments are:
 	- `TRT_LIB_DIR`: Path to the TensorRT installation directory containing libraries.
 	- `TRT_OUT_DIR`: Output directory where generated build artifacts will be copied.
 * Optional CMake build arguments:
 	- `CMAKE_BUILD_TYPE`: Specify if binaries generated are for release or debug (contain debug symbols). Values consists of [`Release`] | `Debug`
-	- `CUDA_VERISON`: The version of CUDA to target, for example [`11.1`].
-	- `CUDNN_VERSION`: The version of cuDNN to target, for example [`8.0`].
-	- `NVCR_SUFFIX`: Optional nvcr/cuda image suffix. Set to "-rc" for CUDA11 RC builds until general availability. Blank by default.
+	- `CUDA_VERISON`: The version of CUDA to target, for example [`11.3.1`].
+	- `CUDNN_VERSION`: The version of cuDNN to target, for example [`8.2`].
 	- `PROTOBUF_VERSION`:  The version of Protobuf to use, for example [`3.0.0`]. Note: Changing this will not configure CMake to use a system version of Protobuf, it will configure CMake to download and try building that version.
 	- `CMAKE_TOOLCHAIN_FILE`: The path to a toolchain file for cross compilation.
 	- `BUILD_PARSERS`: Specify if the parsers should be built, for example [`ON`] | `OFF`.  If turned OFF, CMake will try to find precompiled versions of the parser libraries to use in compiling samples. First in `${TRT_LIB_DIR}`, then on the system. If the build type is Debug, then it will prefer debug builds of the libraries before release versions if available.
@@ -199,13 +180,14 @@ For native builds, install the [prerequisite](#prerequisites) *System Packages*.
 
 ## TensorRT Resources
 
-* [TensorRT Homepage](https://developer.nvidia.com/tensorrt)
+* [TensorRT Developer Home](https://developer.nvidia.com/tensorrt)
+* [TensorRT QuickStart Guide](https://docs.nvidia.com/deeplearning/tensorrt/quick-start-guide/index.html)
 * [TensorRT Developer Guide](https://docs.nvidia.com/deeplearning/tensorrt/developer-guide/index.html)
 * [TensorRT Sample Support Guide](https://docs.nvidia.com/deeplearning/tensorrt/sample-support-guide/index.html)
+* [TensorRT ONNX Tools](https://docs.nvidia.com/deeplearning/tensorrt/index.html#tools)
 * [TensorRT Discussion Forums](https://devtalk.nvidia.com/default/board/304/tensorrt/)
-* [TensorRT Release Notes](https://docs.nvidia.com/deeplearning/tensorrt/release-notes/index.html).
+* [TensorRT Release Notes](https://docs.nvidia.com/deeplearning/tensorrt/release-notes/index.html)
 
 ## Known Issues
 
-#### TensorRT 7.2.3.4
 * None
@@ -1 +1 @@
-7.2.3.4
+8.0.1.6
@@ -32,14 +32,16 @@ set(CMAKE_C_COMPILER_FORCED TRUE)
 set(CMAKE_CXX_COMPILER_FORCED TRUE)
 
 set(CUDA_ROOT /usr/local/cuda-${CUDA_VERSION}/targets/${CUDA_PLATFORM_ID} CACHE STRING "CUDA ROOT dir")
+set(CUDNN_ROOT_DIR /pdk_files/cudnn)
+set(BUILD_LIBRARY_ONLY 1)
 
 set(CUDA_TOOLKIT_ROOT_DIR ${CUDA_ROOT})
 set(CUDA_INCLUDE_DIRS ${CUDA_ROOT}/include)
 
 set(RT_LIB /usr/aarch64-linux-gnu/lib/librt.so)
 
 set(CMAKE_CUDA_HOST_COMPILER ${CMAKE_CXX_COMPILER} CACHE STRING "" FORCE)
-set(CMAKE_CUDA_FLAGS "-cudart none -I${CUDA_INCLUDE_DIRS} -Xcompiler=\"-fPIC ${CMAKE_CXX_FLAGS}\"" CACHE STRING "" FORCE)
+set(CMAKE_CUDA_FLAGS "-I${CUDA_INCLUDE_DIRS} -Xcompiler=\"-fPIC ${CMAKE_CXX_FLAGS}\"" CACHE STRING "" FORCE)
 set(CMAKE_CUDA_COMPILER_FORCED TRUE)
 
 set(CUDA_LIBS -L${CUDA_ROOT}/lib)