8.6.0.12 release updates

Signed-off-by: Shuyue Lan <[email protected]> Signed-off-by: Rajeev Rao <[email protected]>
kelisiya · Mar 17, 2023 · b0b2d3e · b0b2d3e
1 parent f1a4bd3
commit b0b2d3e
Show file tree

Hide file tree

Showing 12 changed files with 47 additions and 34 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -1,5 +1,16 @@
 # TensorRT OSS Release Changelog
 
+## [8.6.0 EA](https://docs.nvidia.com/deeplearning/tensorrt/release-notes/tensorrt-8.html#tensorrt-8) - 2023-03-10
+
+TensorRT OSS release corresponding to TensorRT 8.6.0.12 EA release.
+- Updates since [TensorRT 8.5.3 GA release](https://docs.nvidia.com/deeplearning/tensorrt/release-notes/tensorrt-8.html#rel-8-5-3).
+- Please refer to the [TensorRT 8.6.0.12 EA release notes](https://docs.nvidia.com/deeplearning/tensorrt/release-notes/tensorrt-8.html#tensorrt-8) for more information.
+
+Key Features and Updates:
+
+- demoDiffusion acceleration is now supported out of the box in TensorRT without requiring plugins.
+- Added a new sample called onnx_custom_plugin.
+
 ## [8.5.3 GA](https://docs.nvidia.com/deeplearning/tensorrt/release-notes/tensorrt-8.html#rel-8-5-3) - 2023-01-30
 
 TensorRT OSS release corresponding to TensorRT 8.5.3.1 GA release.
@@ -416,7 +427,7 @@ Identical to the TensorRT-OSS [8.0.1](https://github.com/NVIDIA/TensorRT/release
 
 ## [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](). 
+- 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`.

diff --git a/README.md b/README.md
@@ -25,14 +25,14 @@ You can skip the **Build** section to enjoy TensorRT with Python.
 ## Prerequisites
 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) v8.5.3.1
+**TensorRT EA build**
+* [TensorRT](https://developer.nvidia.com/nvidia-tensorrt-download) v8.6.0.12
 
 **System Packages**
 * [CUDA](https://developer.nvidia.com/cuda-toolkit)
   * Recommended versions:
-  * cuda-11.8.0 + cuDNN-8.6
-  * cuda-10.2 + cuDNN-8.4
+  * cuda-12.0.1 + cuDNN-8.8
+  * cuda-11.8.0 + cuDNN-8.8
 * [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/>) >= v3.6.9, <= v3.10.x
@@ -70,18 +70,18 @@ To build the TensorRT-OSS components, you will first need the following software
 	git submodule update --init --recursive
 	```
 
-2. #### (Optional - if not using TensorRT container) Specify the TensorRT GA release build path
+2. #### (Optional - if not using TensorRT container) Specify the TensorRT EA release build path
 
     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 GA build from [NVIDIA Developer Zone](https://developer.nvidia.com/nvidia-tensorrt-download).
+    Else download and extract the TensorRT EA build from [NVIDIA Developer Zone](https://developer.nvidia.com/nvidia-tensorrt-download).
 
-    **Example: Ubuntu 20.04 on x86-64 with cuda-11.8.0**
+    **Example: Ubuntu 20.04 on x86-64 with cuda-12.0**
 
     ```bash
     cd ~/Downloads
-    tar -xvzf TensorRT-8.5.3.1.Linux.x86_64-gnu.cuda-11.8.cudnn8.6.tar.gz
-    export TRT_LIBPATH=`pwd`/TensorRT-8.5.3.1
+    tar -xvzf TensorRT-8.6.0.12.Linux.x86_64-gnu.cuda-12.0.tar.gz
+    export TRT_LIBPATH=`pwd`/TensorRT-8.6.0.12
     ```
 
 
@@ -99,13 +99,13 @@ For Linux platforms, we recommend that you generate a docker container for build
 1. #### Generate the TensorRT-OSS build container.
     The TensorRT-OSS build container can be generated using the supplied Dockerfiles and build scripts. The build containers are configured for building TensorRT OSS out-of-the-box.
 
-    **Example: Ubuntu 20.04 on x86-64 with cuda-11.8.0 (default)**
+    **Example: Ubuntu 20.04 on x86-64 with cuda-12.0 (default)**
     ```bash
-    ./docker/build.sh --file docker/ubuntu-20.04.Dockerfile --tag tensorrt-ubuntu20.04-cuda11.8
+    ./docker/build.sh --file docker/ubuntu-20.04.Dockerfile --tag tensorrt-ubuntu20.04-cuda12.0
     ```
-    **Example: CentOS/RedHat 7 on x86-64 with cuda-10.2**
+    **Example: CentOS/RedHat 7 on x86-64 with cuda-12.0**
     ```bash
-    ./docker/build.sh --file docker/centos-7.Dockerfile --tag tensorrt-centos7-cuda10.2 --cuda 10.2
+    ./docker/build.sh --file docker/centos-7.Dockerfile --tag tensorrt-centos7-cuda12.0 --cuda 12.0
     ```
     **Example: Ubuntu 20.04 cross-compile for Jetson (aarch64) with cuda-11.4.2 (JetPack SDK)**
     ```bash
@@ -119,7 +119,7 @@ For Linux platforms, we recommend that you generate a docker container for build
 2. #### Launch the TensorRT-OSS build container.
     **Example: Ubuntu 20.04 build container**
 	```bash
-	./docker/launch.sh --tag tensorrt-ubuntu20.04-cuda11.8 --gpus all
+	./docker/launch.sh --tag tensorrt-ubuntu20.04-cuda12.0 --gpus all
 	```
 	> NOTE:
   <br> 1. Use the `--tag` corresponding to build container generated in Step 1.
@@ -130,7 +130,7 @@ For Linux platforms, we recommend that you generate a docker container for build
 ## Building TensorRT-OSS
 * Generate Makefiles and build.
 
-    **Example: Linux (x86-64) build with default cuda-11.8.0**
+    **Example: Linux (x86-64) build with default cuda-12.0**
 	```bash
 	cd $TRT_OSSPATH
 	mkdir -p build && cd build
@@ -146,7 +146,7 @@ For Linux platforms, we recommend that you generate a docker container for build
     export PATH="/opt/rh/devtoolset-8/root/bin:${PATH}
     ```
 
-    **Example: Linux (aarch64) build with default cuda-11.8.0**
+    **Example: Linux (aarch64) build with default cuda-12.0**
 	```bash
 	cd $TRT_OSSPATH
 	mkdir -p build && cd build
@@ -209,4 +209,4 @@ For Linux platforms, we recommend that you generate a docker container for build
 
 ## Known Issues
 
-* Please refer to [TensorRT 8.5 Release Notes](https://docs.nvidia.com/deeplearning/tensorrt/release-notes/tensorrt-8.html#tensorrt-8)
+* Please refer to [TensorRT 8.6 Release Notes](https://docs.nvidia.com/deeplearning/tensorrt/release-notes/tensorrt-8.html#tensorrt-8)
diff --git a/VERSION b/VERSION
@@ -1 +1 @@
-8.5.3.1
+8.6.0.12
diff --git a/docker/build.sh b/docker/build.sh
@@ -18,7 +18,7 @@
 
 arg_dockerfile=docker/ubuntu-20.04.Dockerfile
 arg_imagename=tensorrt-ubuntu
-arg_cudaversion=11.8.0
+arg_cudaversion=12.0.1
 arg_help=0
 
 while [[ "$#" -gt 0 ]]; do case $1 in

diff --git a/docker/centos-7.Dockerfile b/docker/centos-7.Dockerfile
@@ -15,13 +15,13 @@
 # limitations under the License.
 #
 
-ARG CUDA_VERSION=11.8.0
+ARG CUDA_VERSION=12.0.1
 ARG OS_VERSION=7
 
 FROM nvidia/cuda:${CUDA_VERSION}-cudnn8-devel-centos${OS_VERSION}
 LABEL maintainer="NVIDIA CORPORATION"
 
-ENV TRT_VERSION 8.5.3.1
+ENV TRT_VERSION 8.6.0.12
 SHELL ["/bin/bash", "-c"]
 
 # Setup user account
@@ -61,7 +61,7 @@ else \
     yum -y install libnvinfer8-${v} libnvparsers8-${v} libnvonnxparsers8-${v} libnvinfer-plugin8-${v} \
         libnvinfer-devel-${v} libnvparsers-devel-${v} libnvonnxparsers-devel-${v} libnvinfer-plugin-devel-${v} \
         python3-libnvinfer-${v}; \
-fi 
+fi
 
 # Install dev-toolset-8 for g++ version that supports c++14
 RUN yum -y install centos-release-scl

diff --git a/docker/ubuntu-18.04.Dockerfile b/docker/ubuntu-18.04.Dockerfile
@@ -15,13 +15,13 @@
 # limitations under the License.
 #
 
-ARG CUDA_VERSION=11.8.0
+ARG CUDA_VERSION=12.0.1
 ARG OS_VERSION=18.04
 
 FROM nvidia/cuda:${CUDA_VERSION}-cudnn8-devel-ubuntu${OS_VERSION}
 LABEL maintainer="NVIDIA CORPORATION"
 
-ENV TRT_VERSION 8.5.3.1
+ENV TRT_VERSION 8.6.0.12
 SHELL ["/bin/bash", "-c"]
 
 # Setup user account
@@ -78,7 +78,7 @@ else \
     sudo apt-get install libnvinfer8=${v} libnvonnxparsers8=${v} libnvparsers8=${v} libnvinfer-plugin8=${v} \
         libnvinfer-dev=${v} libnvonnxparsers-dev=${v} libnvparsers-dev=${v} libnvinfer-plugin-dev=${v} \
         python3-libnvinfer=${v}; \
-fi 
+fi
 
 # Install PyPI packages
 RUN pip3 install --upgrade pip

diff --git a/docker/ubuntu-20.04-aarch64.Dockerfile b/docker/ubuntu-20.04-aarch64.Dockerfile
@@ -16,9 +16,9 @@
 #
 
 # Multi-arch container support available in non-cudnn containers.
-FROM nvidia/cuda:11.8.0-devel-ubuntu20.04
+FROM nvidia/cuda:12.0.1-devel-ubuntu20.04
 
-ENV TRT_VERSION 8.5.3.1
+ENV TRT_VERSION 8.6.0.12
 SHELL ["/bin/bash", "-c"]
 
 # Setup user account

diff --git a/docker/ubuntu-20.04.Dockerfile b/docker/ubuntu-20.04.Dockerfile
@@ -15,13 +15,13 @@
 # limitations under the License.
 #
 
-ARG CUDA_VERSION=11.8.0
+ARG CUDA_VERSION=12.0.1
 ARG OS_VERSION=20.04
 
 FROM nvidia/cuda:${CUDA_VERSION}-cudnn8-devel-ubuntu${OS_VERSION}
 LABEL maintainer="NVIDIA CORPORATION"
 
-ENV TRT_VERSION 8.5.3.1
+ENV TRT_VERSION 8.6.0.12
 SHELL ["/bin/bash", "-c"]
 
 # Setup user account

diff --git a/docker/ubuntu-cross-aarch64.Dockerfile b/docker/ubuntu-cross-aarch64.Dockerfile
@@ -21,7 +21,7 @@ ARG OS_VERSION=20.04
 FROM nvidia/cuda:${CUDA_VERSION}-devel-ubuntu${OS_VERSION}
 LABEL maintainer="NVIDIA CORPORATION"
 
-ENV TRT_VERSION 8.5.3.1
+ENV TRT_VERSION 8.6.0.12
 ENV DEBIAN_FRONTEND=noninteractive
 
 ARG uid=1000

diff --git a/include/NvInfer.h b/include/NvInfer.h
@@ -9009,7 +9009,9 @@ enum class PreviewFeature : int32_t
     //!
     //! The default value for this flag is on.
     //!
-    kFASTER_DYNAMIC_SHAPES_0805 = 0,
+    //! \deprecated Turning it off is deprecated in TensorRT 8.6. The flag kFASTER_DYNAMIC_SHAPES_0805 will be removed in 9.0.
+    //!
+    kFASTER_DYNAMIC_SHAPES_0805 TRT_DEPRECATED_ENUM = 0,
 
     //!
     //! Disable usage of cuDNN/cuBLAS/cuBLASLt tactics in the TensorRT core library.

diff --git a/include/NvInferPlugin.h b/include/NvInferPlugin.h
@@ -1,5 +1,5 @@
 /*
- * SPDX-FileCopyrightText: Copyright (c) 1993-2022 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+ * SPDX-FileCopyrightText: Copyright (c) 1993-2023 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
  * SPDX-License-Identifier: LicenseRef-NvidiaProprietary
  *
  * NVIDIA CORPORATION, its affiliates and licensors retain all intellectual

diff --git a/include/NvInferVersion.h b/include/NvInferVersion.h
@@ -21,7 +21,7 @@
 #define NV_TENSORRT_MAJOR 8 //!< TensorRT major version.
 #define NV_TENSORRT_MINOR 6 //!< TensorRT minor version.
 #define NV_TENSORRT_PATCH 0 //!< TensorRT patch version.
-#define NV_TENSORRT_BUILD 9 //!< TensorRT build number.
+#define NV_TENSORRT_BUILD 12 //!< TensorRT build number.
 
 #define NV_TENSORRT_LWS_MAJOR 0 //!< TensorRT LWS major version.
 #define NV_TENSORRT_LWS_MINOR 0 //!< TensorRT LWS minor version.