diff --git a/onnxruntime/python/tools/tensorrt/perf/build/build_image.py b/onnxruntime/python/tools/tensorrt/perf/build/build_image.py
index 8cc917cbc7..b98aafc275 100644
--- a/onnxruntime/python/tools/tensorrt/perf/build/build_image.py
+++ b/onnxruntime/python/tools/tensorrt/perf/build/build_image.py
@@ -14,10 +14,9 @@ import sys
 from typing import List, Optional
 
 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",
+    "8.6": "tools/ci_build/github/linux/docker/Dockerfile.ubuntu_cuda11_8_tensorrt8_6",
     "BIN": "tools/ci_build/github/linux/docker/Dockerfile.ubuntu_tensorrt_bin",
 }
 
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 ce34f902e6..98b4d0f29c 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
@@ -10,8 +10,6 @@ parameters:
   type: string
   default: 8.6.0.12
   values:
-  - 8.2.1.8
-  - 8.0.1.6
   - 8.4.1.5
   - 8.5.1.1
   - 8.6.0.12
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
index 9992986f65..e6b6905568 100644
--- 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
@@ -44,7 +44,12 @@ RUN v="8.4.1-1+cuda11.6" &&\
 # Compile trtexec
 RUN cd /usr/src/tensorrt/samples/trtexec && make
 
+ARG BUILD_USER=onnxruntimedev
+ARG BUILD_UID=1000
+RUN adduser --gecos 'onnxruntime Build User' --disabled-password $BUILD_USER --uid $BUILD_UID
+USER $BUILD_USER
 WORKDIR /code
+ENV CUDA_MODULE_LOADING "LAZY"
 
 # Prepare onnxruntime repository & build onnxruntime with TensorRT
 RUN git clone --single-branch --branch ${ONNXRUNTIME_BRANCH} --recursive ${ONNXRUNTIME_REPO} onnxruntime &&\
diff --git a/tools/ci_build/github/linux/docker/Dockerfile.ubuntu_cuda11_8_tensorrt8_5 b/tools/ci_build/github/linux/docker/Dockerfile.ubuntu_cuda11_8_tensorrt8_5
index 920dcf3102..23b0444c6b 100644
--- a/tools/ci_build/github/linux/docker/Dockerfile.ubuntu_cuda11_8_tensorrt8_5
+++ b/tools/ci_build/github/linux/docker/Dockerfile.ubuntu_cuda11_8_tensorrt8_5
@@ -44,6 +44,10 @@ RUN cd /usr/src/tensorrt/samples/trtexec && make
 
 # Build final image from base. Builds ORT.
 FROM base as final
+ARG BUILD_USER=onnxruntimedev
+ARG BUILD_UID=1000
+RUN adduser --gecos 'onnxruntime Build User' --disabled-password $BUILD_USER --uid $BUILD_UID
+USER $BUILD_USER
 
 # ONNX Runtime arguments
 
@@ -76,7 +80,11 @@ RUN if [ -z "$ONNXRUNTIME_COMMIT_ID" ] ; then echo "Building branch ${ONNXRUNTIM
     git reset --hard ${ONNXRUNTIME_COMMIT_ID} && git submodule update --recursive ; fi
 
 # Build ORT
+ENV CUDA_MODULE_LOADING "LAZY"
 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}'"'
 
+# Switch to root to continue following steps of CI
+USER root
+
 # Intall ORT wheel
-RUN pip install ${ONNXRUNTIME_LOCAL_CODE_DIR}/onnxruntime/build/Linux/Release/dist/*.whl
+RUN pip install ${ONNXRUNTIME_LOCAL_CODE_DIR}/onnxruntime/build/Linux/Release/dist/*.whl
\ No newline at end of file
diff --git a/tools/ci_build/github/linux/docker/Dockerfile.ubuntu_cuda11_8_tensorrt8_6 b/tools/ci_build/github/linux/docker/Dockerfile.ubuntu_cuda11_8_tensorrt8_6
index ecc532d3cb..bfc3c95740 100644
--- a/tools/ci_build/github/linux/docker/Dockerfile.ubuntu_cuda11_8_tensorrt8_6
+++ b/tools/ci_build/github/linux/docker/Dockerfile.ubuntu_cuda11_8_tensorrt8_6
@@ -34,9 +34,9 @@ RUN pip install setuptools>=41.0.0
 RUN v="8.6.0.12-1+cuda11.8" &&\
     apt-key adv --fetch-keys https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2004/x86_64/7fa2af80.pub &&\
     apt-get update &&\
-    sudo apt-get install -y libnvinfer8=${v} libnvonnxparsers8=${v} libnvparsers8=${v} libnvinfer-plugin8=${v} libnvinfer-vc-plugin8=${v}\
-        libnvinfer-dev=${v} libnvonnxparsers-dev=${v} libnvparsers-dev=${v} libnvinfer-plugin-dev=${v} libnvinfer-vc-plugin-dev=${v}\
-        python3-libnvinfer=${v} libnvinfer-samples=${v}
+    sudo apt-get install -y libnvinfer8=${v} libnvonnxparsers8=${v} libnvparsers8=${v} libnvinfer-plugin8=${v} libnvinfer-lean8=${v} libnvinfer-vc-plugin8=${v} libnvinfer-dispatch8=${v}\
+        libnvinfer-headers-dev=${v} libnvinfer-headers-plugin-dev=${v} libnvinfer-dev=${v} libnvonnxparsers-dev=${v} libnvparsers-dev=${v} libnvinfer-plugin-dev=${v} libnvinfer-lean-dev=${v} libnvinfer-vc-plugin-dev=${v}  libnvinfer-dispatch-dev=${v}\
+        python3-libnvinfer=${v} libnvinfer-samples=${v} tensorrt-dev=${v} tensorrt-libs=${v}
 
 # Compile trtexec
 RUN cd /usr/src/tensorrt/samples/trtexec && make
@@ -44,6 +44,10 @@ RUN cd /usr/src/tensorrt/samples/trtexec && make
 
 # Build final image from base. Builds ORT.
 FROM base as final
+ARG BUILD_USER=onnxruntimedev
+ARG BUILD_UID=1000
+RUN adduser --gecos 'onnxruntime Build User' --disabled-password $BUILD_USER --uid $BUILD_UID
+USER $BUILD_USER
 
 # ONNX Runtime arguments
 
@@ -76,7 +80,11 @@ RUN if [ -z "$ONNXRUNTIME_COMMIT_ID" ] ; then echo "Building branch ${ONNXRUNTIM
     git reset --hard ${ONNXRUNTIME_COMMIT_ID} && git submodule update --recursive ; fi
 
 # Build ORT
+ENV CUDA_MODULE_LOADING "LAZY"
 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}'"'
 
+# Switch to root to continue following steps of CI
+USER root
+
 # Intall ORT wheel
-RUN pip install ${ONNXRUNTIME_LOCAL_CODE_DIR}/onnxruntime/build/Linux/Release/dist/*.whl
+RUN pip install ${ONNXRUNTIME_LOCAL_CODE_DIR}/onnxruntime/build/Linux/Release/dist/*.whl
\ No newline at end of file