[EP Perf Dashboard] Add TensorRT 8.5.1.1 dockerfile (#13843)

### Description
- Adds a dockerfile for Ubuntu with TensorRT 8.5.1.1.
- Adds option to run EP Perf pipeline with TensorRT 8.5

### Motivation and Context
Necessary to benchmark models with TensorRT 8.5

onnxruntime/python/tools/tensorrt/perf/build/build_image.py

@@ -17,6 +17,7 @@ TRT_DOCKER_FILES = {
     "8.0": "tools/ci_build/github/linux/docker/Dockerfile.ubuntu_cuda11_4_tensorrt8_0",
     "8.2": "tools/ci_build/github/linux/docker/Dockerfile.ubuntu_cuda11_4_tensorrt8_2",
     "8.4": "tools/ci_build/github/linux/docker/Dockerfile.ubuntu_cuda11_6_tensorrt8_4",
+    "8.5": "tools/ci_build/github/linux/docker/Dockerfile.ubuntu_cuda11_8_tensorrt8_5",
     "BIN": "tools/ci_build/github/linux/docker/Dockerfile.ubuntu_tensorrt_bin",
 }
 

tools/ci_build/github/azure-pipelines/linux-gpu-tensorrt-daily-perf-pipeline.yml

@@ -13,6 +13,7 @@ parameters:
   - 8.2.1.8
   - 8.0.1.6
   - 8.4.1.5
+  - 8.5.1.1
   - BIN
 
 - name: ModelGroups

tools/ci_build/github/linux/docker/Dockerfile.ubuntu_cuda11_8_tensorrt8_5

@@ -0,0 +1,82 @@
+# --------------------------------------------------------------
+# Copyright (c) Microsoft Corporation. All rights reserved.
+# Licensed under the MIT License.
+# --------------------------------------------------------------
+# Dockerfile to run ONNXRuntime with TensorRT integration
+
+# Build base image with required system packages
+FROM nvidia/cuda:11.8.0-cudnn8-devel-ubuntu20.04 AS base
+
+# The local directory into which to build and install CMAKE
+ARG ONNXRUNTIME_LOCAL_CODE_DIR=/code
+
+ENV PATH /usr/local/nvidia/bin:/usr/local/cuda/bin:/usr/src/tensorrt/bin:${ONNXRUNTIME_LOCAL_CODE_DIR}/cmake-3.24.3-linux-x86_64/bin:/opt/miniconda/bin:${PATH}
+ENV DEBIAN_FRONTEND=noninteractive
+
+RUN apt-get update &&\
+    apt-get install -y sudo git bash unattended-upgrades wget
+RUN unattended-upgrade
+
+# Install python3
+RUN apt-get install -y --no-install-recommends \
+    python3 \
+    python3-pip \
+    python3-dev \
+    python3-wheel &&\
+    cd /usr/local/bin &&\
+    ln -s /usr/bin/python3 python &&\
+    ln -s /usr/bin/pip3 pip;
+
+RUN pip install --upgrade pip 
+RUN pip install setuptools>=41.0.0
+
+# Install TensorRT
+RUN v="8.5.1-1+cuda11.8" &&\
+    apt-key adv --fetch-keys https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2004/x86_64/7fa2af80.pub &&\
+    apt-get update &&\
+    sudo apt-get install -y libnvinfer8=${v} libnvonnxparsers8=${v} libnvparsers8=${v} libnvinfer-plugin8=${v} \
+        libnvinfer-dev=${v} libnvonnxparsers-dev=${v} libnvparsers-dev=${v} libnvinfer-plugin-dev=${v} \
+        python3-libnvinfer=${v} libnvinfer-samples=${v}
+
+# Compile trtexec
+RUN cd /usr/src/tensorrt/samples/trtexec && make
+
+
+# Build final image from base. Builds ORT.
+FROM base as final
+
+# ONNX Runtime arguments
+
+# URL to the github repo from which to clone ORT.
+ARG ONNXRUNTIME_REPO=https://github.com/Microsoft/onnxruntime
+
+# The local directory into which to clone ORT.
+ARG ONNXRUNTIME_LOCAL_CODE_DIR=/code
+
+# The git branch of ORT to checkout and build.
+ARG ONNXRUNTIME_BRANCH=main
+
+# Optional. The specific commit to pull and build from. If not set, the latest commit is used.
+ARG ONNXRUNTIME_COMMIT_ID
+
+# The supported CUDA architecture
+ARG CMAKE_CUDA_ARCHITECTURES=37;50;52;60;61;70;75;80
+
+WORKDIR ${ONNXRUNTIME_LOCAL_CODE_DIR}
+
+# Clone ORT repository with branch
+RUN git clone --single-branch --branch ${ONNXRUNTIME_BRANCH} --recursive ${ONNXRUNTIME_REPO} onnxruntime &&\
+    /bin/sh onnxruntime/dockerfiles/scripts/install_common_deps.sh
+
+WORKDIR ${ONNXRUNTIME_LOCAL_CODE_DIR}/onnxruntime
+
+# Reset to a specific commit if specified by build args.
+RUN if [ -z "$ONNXRUNTIME_COMMIT_ID" ] ; then echo "Building branch ${ONNXRUNTIME_BRANCH}" ;\
+    else echo "Building branch ${ONNXRUNTIME_BRANCH} @ commit ${ONNXRUNTIME_COMMIT_ID}" &&\
+    git reset --hard ${ONNXRUNTIME_COMMIT_ID} && git submodule update --recursive ; fi
+
+# Build ORT
+RUN /bin/sh build.sh --parallel --build_shared_lib --cuda_home /usr/local/cuda --cudnn_home /usr/lib/x86_64-linux-gnu/ --use_tensorrt --tensorrt_home /usr/lib/x86_64-linux-gnu/ --config Release --build_wheel --skip_tests --skip_submodule_sync --cmake_extra_defines '"CMAKE_CUDA_ARCHITECTURES='${CMAKE_CUDA_ARCHITECTURES}'"'
+
+# Intall ORT wheel
+RUN pip install ${ONNXRUNTIME_LOCAL_CODE_DIR}/onnxruntime/build/Linux/Release/dist/*.whl