diff --git a/onnxruntime/python/tools/tensorrt/perf/perf.sh b/onnxruntime/python/tools/tensorrt/perf/perf.sh
index 8844e77a4d..5f67156043 100755
--- a/onnxruntime/python/tools/tensorrt/perf/perf.sh
+++ b/onnxruntime/python/tools/tensorrt/perf/perf.sh
@@ -53,7 +53,7 @@ download_files() {
 setup() {
     apt update
     apt-get install -y --no-install-recommends pciutils
-    pip install --upgrade pip 
+    pip install --upgrade pip
     pip install -r requirements.txt    
     if [ "$BUILD_ORT" = "False" ]
     then
diff --git a/tools/ci_build/github/azure-pipelines/linux-gpu-tensorrt-daily-perf-pipeline.yml b/tools/ci_build/github/azure-pipelines/linux-gpu-tensorrt-daily-perf-pipeline.yml
index 276b2724e3..b347ede296 100644
--- a/tools/ci_build/github/azure-pipelines/linux-gpu-tensorrt-daily-perf-pipeline.yml
+++ b/tools/ci_build/github/azure-pipelines/linux-gpu-tensorrt-daily-perf-pipeline.yml
@@ -13,15 +13,16 @@ parameters:
 - name: RunNvidiaContainer
   displayName: Run in Nvidia Container (or set trtContainer Variable)
   type: boolean
-  default: true
+  default: false
 
 - name: TrtVersion
   displayName: TensorRT Version
   type: string
-  default: 8.2.1.8
+  default: 8.4.1.5
   values:
   - 8.2.1.8
   - 8.0.1.6
+  - 8.4.1.5
 
 - name: ConfigureEPs
   displayName: Configure EPs (set epList variable - separate by spaces)
@@ -81,7 +82,9 @@ jobs:
       ${{ if eq(parameters.RunNvidiaContainer, true) }}:
         value: $(dockerfile_path)/Dockerfile.tensorrt
       ${{ else }}:
-        ${{ if eq(parameters.TrtVersion, '8.2.1.8') }}:
+        ${{ if eq(parameters.TrtVersion, '8.4.1.5') }}:
+          value: $(dockerfile_path)/Dockerfile.ubuntu_cuda11_6_tensorrt8_4
+        ${{ elseif eq(parameters.TrtVersion, '8.2.1.8') }}:
           value: $(dockerfile_path)/Dockerfile.ubuntu_cuda11_4_tensorrt8_2
         ${{ elseif eq(parameters.TrtVersion, '8.0.1.6') }}:
           value: $(dockerfile_path)/Dockerfile.ubuntu_cuda11_4_tensorrt8_0
@@ -123,12 +126,12 @@ jobs:
           artifact: 'onnxruntime_gpu'
           targetPath: '$(Build.SourcesDirectory)/onnxruntime/python/tools/tensorrt/perf/'
       
-    - ${{ if eq(parameters.RunNvidiaContainer, true) }}:
-      - script: 'docker pull $(nvidia_dockerfile)'
-        displayName: 'Pull Nvidia Dockerfile'
-    - ${{ if eq(parameters.RunNvidiaContainer, false) }}:
-      - script: 'Can only run pip package in Nvidia Container'
-        displayName: 'Please Re-run'
+      - ${{ if eq(parameters.RunNvidiaContainer, true) }}:
+        - script: 'docker pull $(nvidia_dockerfile)'
+          displayName: 'Pull Nvidia Dockerfile'
+      - ${{ else }}:
+        - script: 'Can only run pip package in Nvidia Container'
+          displayName: 'Please Re-run'
 
     - ${{ if eq(parameters.BuildORT, true) }}:
       - script: '$(Build.SourcesDirectory)/onnxruntime/python/tools/tensorrt/perf/build/build_image.sh -o $(Build.SourcesDirectory)/$(dockerfile) -b $(branch) -t $(tensorrt_version) -i $(image) -c 75 '
diff --git a/tools/ci_build/github/linux/docker/Dockerfile.ubuntu_cuda11_6_tensorrt8_4 b/tools/ci_build/github/linux/docker/Dockerfile.ubuntu_cuda11_6_tensorrt8_4
new file mode 100644
index 0000000000..2af158dc43
--- /dev/null
+++ b/tools/ci_build/github/linux/docker/Dockerfile.ubuntu_cuda11_6_tensorrt8_4
@@ -0,0 +1,55 @@
+# --------------------------------------------------------------
+# Copyright (c) Microsoft Corporation. All rights reserved.
+# Licensed under the MIT License.
+# --------------------------------------------------------------
+# Dockerfile to run ONNXRuntime with TensorRT integration
+
+FROM nvidia/cuda:11.6.1-cudnn8-devel-ubuntu20.04
+
+
+# ONNX Runtime Variables
+ARG ONNXRUNTIME_REPO=https://github.com/Microsoft/onnxruntime
+ARG ONNXRUNTIME_BRANCH=master
+ARG CMAKE_CUDA_ARCHITECTURES=37;50;52;60;61;70;75;80
+
+ENV PATH /usr/local/nvidia/bin:/usr/local/cuda/bin:/usr/src/tensorrt/bin:/code/cmake-3.21.0-linux-x86_64/bin:/opt/miniconda/bin:${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="8.4.1-1+cuda11.6" &&\
+    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
+
+WORKDIR /code
+
+# Prepare onnxruntime repository & build onnxruntime with TensorRT
+RUN git clone --single-branch --branch ${ONNXRUNTIME_BRANCH} --recursive ${ONNXRUNTIME_REPO} onnxruntime &&\
+    /bin/sh onnxruntime/dockerfiles/scripts/install_common_deps.sh &&\
+    cd onnxruntime &&\
+    /bin/sh build.sh --parallel --build_shared_lib --cuda_home /usr/local/cuda --cudnn_home /usr/lib/x86_64-linux-gnu/ --use_tensorrt --tensorrt_home /usr/lib/x86_64-linux-gnu/ --config Release --build_wheel --skip_tests --skip_submodule_sync --cmake_extra_defines '"CMAKE_CUDA_ARCHITECTURES='${CMAKE_CUDA_ARCHITECTURES}'"' &&\
+    pip install /code/onnxruntime/build/Linux/Release/dist/*.whl &&\
+    cd ..