diff --git a/onnxruntime/python/tools/transformers/models/sam2/README.md b/onnxruntime/python/tools/transformers/models/sam2/README.md
index 26385896aa..e7cafeffc6 100644
--- a/onnxruntime/python/tools/transformers/models/sam2/README.md
+++ b/onnxruntime/python/tools/transformers/models/sam2/README.md
@@ -89,13 +89,15 @@ It is able to run demo on optimized model as well. For example,
 python3 convert_to_onnx.py  --sam2_dir $sam2_dir --optimize --dtype fp16 --use_gpu --demo
 ```
 
-## Benchmark
+## Benchmark and Profiling
 
 We can create a conda environment then run GPU benchmark like the following:
 ```bash
 conda create -n sam2_gpu python=3.11 -y
 conda activate sam2_gpu
-bash benchmark_sam2.sh $HOME gpu
+install_dir=$HOME
+profiling=true
+bash benchmark_sam2.sh $install_dir gpu $profiling
 ```
 
 or create a new conda environment for CPU benchmark:
@@ -107,13 +109,14 @@ bash benchmark_sam2.sh $HOME cpu
 
 The first parameter is a directory to clone git repositories or install CUDA/cuDNN for benchmark.
 The second parameter can be either "gpu" or "cpu", which indicates the device to run benchmark.
+The third parameter is optional. Value "true" will enable profiling after running benchmarking on GPU.
 
 The script will automatically install required packages in current conda environment, download checkpoints, export onnx,
-and run demo, benchmark and profiling.
+and run demo, benchmark and optionally run profiling.
 
 * The performance test result is in sam2_gpu.csv or sam2_cpu.csv, which can be loaded into Excel.
 * The demo output is sam2_demo_fp16_gpu.png or sam2_demo_fp32_cpu.png.
-* The profiling results are in *.nsys-rep or *.json files in current directory.
+* The profiling results are in *.nsys-rep or *.json files in current directory. Use Nvidia NSight System to view the *.nsys-rep file.
 
 ## Limitations
 - The exported image_decoder model does not support batch mode for now.
diff --git a/onnxruntime/python/tools/transformers/models/sam2/benchmark_sam2.py b/onnxruntime/python/tools/transformers/models/sam2/benchmark_sam2.py
index 7e108b1638..f75a4527be 100644
--- a/onnxruntime/python/tools/transformers/models/sam2/benchmark_sam2.py
+++ b/onnxruntime/python/tools/transformers/models/sam2/benchmark_sam2.py
@@ -90,26 +90,23 @@ class TestConfig:
         else:
             return decoder_shape_dict(self.height, self.width, self.num_labels, self.num_points, self.num_masks)
 
-    def random_inputs(self):
+    def random_inputs(self) -> Mapping[str, torch.Tensor]:
+        dtype = self.dtype
         if self.component == "image_encoder":
-            return {
-                "image": torch.randn(
-                    self.batch_size, 3, self.height, self.width, dtype=torch.float32, device=self.device
-                )
-            }
+            return {"image": torch.randn(self.batch_size, 3, self.height, self.width, dtype=dtype, device=self.device)}
         else:
             return {
-                "image_features_0": torch.rand(1, 32, 256, 256, dtype=torch.float32, device=self.device),
-                "image_features_1": torch.rand(1, 64, 128, 128, dtype=torch.float32, device=self.device),
-                "image_embeddings": torch.rand(1, 256, 64, 64, dtype=torch.float32, device=self.device),
+                "image_features_0": torch.rand(1, 32, 256, 256, dtype=dtype, device=self.device),
+                "image_features_1": torch.rand(1, 64, 128, 128, dtype=dtype, device=self.device),
+                "image_embeddings": torch.rand(1, 256, 64, 64, dtype=dtype, device=self.device),
                 "point_coords": torch.randint(
-                    0, 1024, (self.num_labels, self.num_points, 2), dtype=torch.float32, device=self.device
+                    0, 1024, (self.num_labels, self.num_points, 2), dtype=dtype, device=self.device
                 ),
                 "point_labels": torch.randint(
                     0, 1, (self.num_labels, self.num_points), dtype=torch.int32, device=self.device
                 ),
-                "input_masks": torch.zeros(self.num_labels, 1, 256, 256, dtype=torch.float32, device=self.device),
-                "has_input_masks": torch.ones(self.num_labels, dtype=torch.float32, device=self.device),
+                "input_masks": torch.zeros(self.num_labels, 1, 256, 256, dtype=dtype, device=self.device),
+                "has_input_masks": torch.ones(self.num_labels, dtype=dtype, device=self.device),
                 "original_image_size": torch.tensor([self.height, self.width], dtype=torch.int32, device=self.device),
             }
 
@@ -314,7 +311,7 @@ def run_test(
         width=args.width,
         device=device,
         use_tf32=True,
-        enable_cuda_graph=False,
+        enable_cuda_graph=enable_cuda_graph,
         dtype=dtypes[args.dtype],
         prefer_nhwc=args.prefer_nhwc,
         repeats=args.repeats,
diff --git a/onnxruntime/python/tools/transformers/models/sam2/benchmark_sam2.sh b/onnxruntime/python/tools/transformers/models/sam2/benchmark_sam2.sh
index f8c5abdb75..e6da988f5c 100644
--- a/onnxruntime/python/tools/transformers/models/sam2/benchmark_sam2.sh
+++ b/onnxruntime/python/tools/transformers/models/sam2/benchmark_sam2.sh
@@ -1,48 +1,35 @@
 #!/bin/bash
 # -------------------------------------------------------------------------
-# Copyright (c) Microsoft Corporation.  All rights reserved.
+# Copyright (c) Microsoft Corporation. All rights reserved.
 # Licensed under the MIT License.
-# --------------------------------------------------------------------------
+# -------------------------------------------------------------------------
 
-# Here assumes that we are using conda (Anaconda/Miniconda/Miniforge) environment.
-# For example, you can create a new conda environment like the following before running this script:
-#    conda create -n sam2_gpu python=3.11 -y
-#    conda activate sam2_gpu
-#    bash benchmark_sam2.sh $HOME gpu
-# Or create a new conda environment for CPU benchmark:
-#    conda create -n sam2_cpu python=3.11 -y
-#    conda activate sam2_cpu
-#    bash benchmark_sam2.sh $HOME cpu
+# Please refer to README.md for the prerequisites and usage of this script.
+#   bash benchmark_sam2.sh <install_dir> <cpu|gpu> [profiling]
 
-python=$CONDA_PREFIX/bin/python3
+python="$CONDA_PREFIX/bin/python3"
 
-# Directory of the script
-dir="$( cd "$( dirname "$0" )" && pwd )"
+# Directory of the script and ONNX models
+dir="$(cd "$(dirname "$0")" && pwd)"
+onnx_dir="$dir/sam2_onnx_models"
 
-# Directory of the onnx models
-onnx_dir=$dir/sam2_onnx_models
+# Installation directory (default: $HOME)
+install_dir="${1:-$HOME}"
 
-# Directory to install CUDA, cuDNN, and git clone sam2 or onnxruntime source code.
-install_dir=$HOME
-if [ $# -ge 1 ]; then
-    install_dir=$1
-fi
-
-if ! [ -d $install_dir ]; then
-    echo "install_dir: $install_dir does not exist."
+if [ ! -d "$install_dir" ]; then
+    echo "Error: install_dir '$install_dir' does not exist."
     exit 1
 fi
 
-# Directory of the sam2 code by "git clone https://github.com/facebookresearch/segment-anything-2"
-sam2_dir=$install_dir/segment-anything-2
+# SAM2 code directory and model to benchmark
+sam2_dir="$install_dir/segment-anything-2"
+model="sam2_hiera_large"
 
-# model name to benchmark
-model=sam2_hiera_large
-
-# Default to use GPU if available.
-cpu_or_gpu="gpu"
-if [ $# -ge 2 ] && ([ "$2" = "gpu" ] || [ "$2" = "cpu" ]); then
-    cpu_or_gpu=$2
+# Default to GPU, switch to CPU if specified
+cpu_or_gpu="${2:-gpu}"
+if [ "$cpu_or_gpu" != "gpu" ] && [ "$cpu_or_gpu" != "cpu" ]; then
+    echo "Invalid option: $2. Please specify 'cpu' or 'gpu'."
+    exit 1
 fi
 
 echo "install_dir: $install_dir"
@@ -51,148 +38,156 @@ echo "cpu_or_gpu: $cpu_or_gpu"
 install_cuda_12()
 {
     pushd $install_dir
-    wget https://developer.download.nvidia.com/compute/cuda/12.5.1/local_installers/cuda_12.5.1_555.42.06_linux.run
-    sh cuda_12.5.1_555.42.06_linux.run --toolkit --toolkitpath=$install_dir/cuda12.5 --silent --override --no-man-page
+    wget https://developer.download.nvidia.com/compute/cuda/12.6.2/local_installers/cuda_12.6.2_560.35.03_linux.run
+    sh cuda_12.6.2_560.35.03_linux.run --toolkit --toolkitpath=$install_dir/cuda12.6 --silent --override --no-man-page
 
-    export PATH="$install_dir/cuda12.5/bin:$PATH"
-    export LD_LIBRARY_PATH="$install_dir/cuda12.5/lib64:$LD_LIBRARY_PATH"
+    export PATH="$install_dir/cuda12.6/bin:$PATH"
+    export LD_LIBRARY_PATH="$install_dir/cuda12.6/lib64:$LD_LIBRARY_PATH"
     popd
 }
 
-install_cudnn_9()
-{
-    pushd $install_dir
-    wget  https://developer.download.nvidia.com/compute/cudnn/redist/cudnn/linux-x86_64/cudnn-linux-x86_64-9.4.0.58_cuda12-archive.tar.xz
-    mkdir $install_dir/cudnn9.4
-    tar -Jxvf cudnn-linux-x86_64-9.4.0.58_cuda12-archive.tar.xz -C $install_dir/cudnn9.4 --strip=1  --no-overwrite-dir
-
-    export LD_LIBRARY_PATH="$install_dir/cudnn9.4/lib:$LD_LIBRARY_PATH"
+# Function to install cuDNN 9.4
+install_cudnn_9() {
+    pushd "$install_dir"
+    wget -q https://developer.download.nvidia.com/compute/cudnn/redist/cudnn/linux-x86_64/cudnn-linux-x86_64-9.5.0.50_cuda12-archive.tar.xz
+    mkdir -p "$install_dir/cudnn9.5"
+    tar -Jxvf cudnn-linux-x86_64-9.5.0.50_cuda12-archive.tar.xz -C "$install_dir/cudnn9.5" --strip=1
+    export LD_LIBRARY_PATH="$install_dir/cudnn9.5/lib:$LD_LIBRARY_PATH"
     popd
 }
 
-install_gpu()
-{
-    if ! [ -d $install_dir/cuda12.5 ]; then
-        install_cuda_12
-    fi
-
-    if ! [ -d $install_dir/cudnn9.4 ]; then
-        install_cudnn_9
-    fi
+# Install GPU dependencies
+install_gpu() {
+    [ ! -d "$install_dir/cuda12.6" ] && install_cuda_12
+    [ ! -d "$install_dir/cudnn9.5" ] && install_cudnn_9
 
     pip install torch torchvision --index-url https://download.pytorch.org/whl/cu124
     pip install onnxruntime-gpu onnx opencv-python matplotlib
 }
 
-install_cpu()
-{
+# Install CPU dependencies
+install_cpu() {
     pip install torch torchvision --index-url https://download.pytorch.org/whl/cpu
     pip install onnxruntime onnx opencv-python matplotlib
 }
 
-install_sam2()
-{
-    pushd $install_dir
-
-    if ! [ -d $install_dir/segment-anything-2 ]; then
+# Clone and install SAM2 if not already installed
+install_sam2() {
+    pushd "$install_dir"
+    if [ ! -d "$sam2_dir" ]; then
         git clone https://github.com/facebookresearch/segment-anything-2.git
     fi
-
-    cd segment-anything-2
-
-    if pip show SAM-2 > /dev/null 2>&1; then
-        echo "SAM-2 is already installed."
-    else
-        pip install -e .
-    fi
-
-    if ! [ -f checkpoints/sam2_hiera_large.pt ]; then
-        echo "Downloading checkpoints..."
-        cd checkpoints
-        sh ./download_ckpts.sh
-    fi
-
+    cd "$sam2_dir"
+    pip show SAM-2 > /dev/null 2>&1 || pip install -e .
+    [ ! -f checkpoints/sam2_hiera_large.pt ] && (cd checkpoints && sh ./download_ckpts.sh)
     popd
 }
 
-download_test_image()
-{
-    if ! [ -f truck.jpg ]; then
-        curl https://raw.githubusercontent.com/facebookresearch/segment-anything-2/main/notebooks/images/truck.jpg > truck.jpg
+# Download test image if not available
+download_test_image() {
+    [ ! -f truck.jpg ] && curl -sO https://raw.githubusercontent.com/facebookresearch/segment-anything-2/main/notebooks/images/truck.jpg
+}
+
+run_cpu_benchmark() {
+    local repeats="$1"
+    $python convert_to_onnx.py --sam2_dir "$sam2_dir" --optimize --demo
+
+    for component in image_encoder image_decoder; do
+        $python benchmark_sam2.py --model_type "$model" --engine torch --sam2_dir "$sam2_dir" --repeats "$repeats" --dtype fp32 --component "$component"
+
+        # Run ONNX Runtime on exported model (not optimized)
+        $python benchmark_sam2.py --model_type "$model" --engine ort --sam2_dir "$sam2_dir" --repeats "$repeats" --onnx_path "${onnx_dir}/${model}_${component}.onnx" --dtype fp32 --component "$component"
+
+        # Run ONNX Runtime on optimized model
+        $python benchmark_sam2.py --model_type "$model" --engine ort --sam2_dir "$sam2_dir" --repeats "$repeats" --onnx_path "${onnx_dir}/${model}_${component}_fp32_cpu.onnx" --dtype fp32 --component "$component"
+    done
+}
+
+run_gpu_benchmark() {
+    local repeats="$1"
+    $python convert_to_onnx.py --sam2_dir "$sam2_dir" --optimize --use_gpu --dtype fp32
+    $python convert_to_onnx.py --sam2_dir "$sam2_dir" --optimize --use_gpu --dtype fp16 --demo
+
+    for component in image_encoder image_decoder; do
+        for dtype in bf16 fp32 fp16; do
+            $python benchmark_sam2.py --model_type "$model" --engine torch --sam2_dir "$sam2_dir" --repeats "$repeats" --use_gpu --dtype $dtype --component "$component"
+        done
+    done
+
+    component="image_encoder"
+    for dtype in fp32 fp16; do
+        #TODO: --prefer_nhwc does not help with performance
+        $python benchmark_sam2.py --model_type "$model" --engine ort --sam2_dir "$sam2_dir" --repeats "$repeats" --use_gpu --dtype $dtype --component "$component" --onnx_path "${onnx_dir}/${model}_${component}_${dtype}_gpu.onnx" --use_cuda_graph
+    done
+
+    component="image_decoder"
+    for dtype in fp32 fp16; do
+        # TODO: decoder does not work with cuda graph
+        $python benchmark_sam2.py --model_type "$model" --engine ort --sam2_dir "$sam2_dir" --repeats "$repeats" --use_gpu --dtype $dtype --component "$component" --onnx_path "${onnx_dir}/${model}_${component}_${dtype}_gpu.onnx"
+    done
+}
+
+run_torch_compile_gpu_benchmark() {
+    local repeats="$1"
+
+    # Test different torch compile modes on image encoder
+    for torch_compile_mode in none max-autotune reduce-overhead max-autotune-no-cudagraphs
+    do
+        $python benchmark_sam2.py --model_type $model --engine torch --sam2_dir "$sam2_dir" --repeats "$repeats" --use_gpu --dtype fp16 --component image_encoder --torch_compile_mode $torch_compile_mode
+    done
+}
+
+
+# Main script
+run_benchmarks() {
+    if [ ! -v CONDA_PREFIX ]; then
+        echo "Please activate conda environment before running this script."
+        exit 1
+    fi
+
+    # Install dependencies
+    [ "$cpu_or_gpu" = "gpu" ] && install_gpu || install_cpu
+    install_sam2
+    download_test_image
+
+    # Run benchmarks
+    output_csv="sam2_${cpu_or_gpu}.csv"
+    if [ ! -f "$output_csv" ]; then
+        echo "Running $cpu_or_gpu benchmark..."
+        if [ "$cpu_or_gpu" = "gpu" ]; then
+            run_gpu_benchmark 1000
+            run_torch_compile_gpu_benchmark 1000
+        else
+            run_cpu_benchmark 100
+        fi
+        cat benchmark*.csv > combined_csv
+        awk '!x[$0]++' combined_csv > "$output_csv"
+        rm combined_csv
+        echo "Benchmark results saved in $output_csv"
+    else
+        echo "$output_csv already exists, skipping benchmark..."
     fi
 }
 
-run_cpu()
-{
-    repeats=$1
+run_benchmarks
 
-    $python convert_to_onnx.py  --sam2_dir $sam2_dir --optimize --demo
+#--------------------------------------------------------------------------
+# Below are for profiling
+#--------------------------------------------------------------------------
 
-    echo "Benchmarking SAM2 model $model image encoder for PyTorch ..."
-    $python benchmark_sam2.py --model_type $model --engine torch --sam2_dir $sam2_dir --repeats $repeats --dtype fp32
-    $python benchmark_sam2.py --model_type $model --engine torch --sam2_dir $sam2_dir --repeats $repeats --dtype fp16
-
-    echo "Benchmarking SAM2 model $model image encoder for PyTorch ..."
-    $python benchmark_sam2.py --model_type $model --engine torch --sam2_dir $sam2_dir --repeats $repeats --dtype fp32 --component image_decoder
-    $python benchmark_sam2.py --model_type $model --engine torch --sam2_dir $sam2_dir --repeats $repeats --dtype fp16 --component image_decoder
-
-    echo "Benchmarking SAM2 model $model image encoder for ORT ..."
-    $python benchmark_sam2.py --model_type $model --engine ort --sam2_dir $sam2_dir --repeats $repeats --onnx_path ${onnx_dir}/${model}_image_encoder.onnx --dtype fp32
-    $python benchmark_sam2.py --model_type $model --engine ort --sam2_dir $sam2_dir --repeats $repeats --onnx_path ${onnx_dir}/${model}_image_encoder_fp32_cpu.onnx --dtype fp32
-
-    echo "Benchmarking SAM2 model $model image decoder for ORT ..."
-    $python benchmark_sam2.py --model_type $model --engine ort --sam2_dir $sam2_dir --repeats $repeats --onnx_path ${onnx_dir}/${model}_image_decoder.onnx --component image_decoder
-    $python benchmark_sam2.py --model_type $model --engine ort --sam2_dir $sam2_dir --repeats $repeats --onnx_path ${onnx_dir}/${model}_image_decoder_fp32_cpu.onnx --component image_decoder
-}
-
-run_gpu()
-{
-    repeats=$1
-
-    $python convert_to_onnx.py  --sam2_dir $sam2_dir --optimize --use_gpu --dtype fp32
-    $python convert_to_onnx.py  --sam2_dir $sam2_dir --optimize --use_gpu --dtype fp16 --demo
-
-    echo "Benchmarking SAM2 model $model image encoder for PyTorch ..."
-    $python benchmark_sam2.py --model_type $model --engine torch --sam2_dir $sam2_dir --repeats $repeats --use_gpu --dtype bf16
-    $python benchmark_sam2.py --model_type $model --engine torch --sam2_dir $sam2_dir --repeats $repeats --use_gpu --dtype fp32
-
-    # Test different torch compile modes on image encoder (none will disable compile and use eager mode).
-    for torch_compile_mode in none max-autotune reduce-overhead max-autotune-no-cudagraphs
-    do
-        $python benchmark_sam2.py --model_type $model --engine torch --sam2_dir $sam2_dir --repeats $repeats --use_gpu --dtype fp16 --component image_encoder --torch_compile_mode $torch_compile_mode
-    done
-
-    echo "Benchmarking SAM2 model $model image decoder for PyTorch ..."
-    $python benchmark_sam2.py --model_type $model --engine torch --sam2_dir $sam2_dir --repeats $repeats --use_gpu --dtype bf16 --component image_decoder
-    $python benchmark_sam2.py --model_type $model --engine torch --sam2_dir $sam2_dir --repeats $repeats --use_gpu --dtype fp32 --component image_decoder
-    $python benchmark_sam2.py --model_type $model --engine torch --sam2_dir $sam2_dir --repeats $repeats --use_gpu --dtype fp16 --component image_decoder
-
-    echo "Benchmarking SAM2 model $model image encoder for ORT ..."
-    $python benchmark_sam2.py --model_type $model --engine ort --sam2_dir $sam2_dir --repeats $repeats --onnx_path ${onnx_dir}/${model}_image_encoder_fp16_gpu.onnx --use_gpu --dtype fp16
-    $python benchmark_sam2.py --model_type $model --engine ort --sam2_dir $sam2_dir --repeats $repeats --onnx_path ${onnx_dir}/${model}_image_encoder_fp32_gpu.onnx --use_gpu --dtype fp32
-
-    echo "Benchmarking SAM2 model $model image decoder for ORT ..."
-    $python benchmark_sam2.py --model_type $model --engine ort --sam2_dir $sam2_dir --repeats $repeats --onnx_path ${onnx_dir}/${model}_image_decoder_fp16_gpu.onnx --component image_decoder --use_gpu --dtype fp16
-    $python benchmark_sam2.py --model_type $model --engine ort --sam2_dir $sam2_dir --repeats $repeats --onnx_path ${onnx_dir}/${model}_image_decoder_fp32_gpu.onnx --component image_decoder --use_gpu
-}
-
-# Build onnxruntime-gpu from source for profiling.
-build_onnxruntime_gpu_for_profiling()
-{
-    pushd $install_dir
+# Build onnxruntime-gpu from source for profiling
+build_onnxruntime_gpu_for_profiling() {
+    pushd "$install_dir"
     if ! [ -d onnxruntime ]; then
         git clone https://github.com/microsoft/onnxruntime
     fi
     cd onnxruntime
-
-    # Get the CUDA compute capability of the GPU.
     CUDA_ARCH=$(python3 -c "import torch; cc = torch.cuda.get_device_capability(); print(f'{cc[0]}{cc[1]}')")
-
     if [ -n "$CUDA_ARCH" ]; then
         pip install --upgrade pip cmake psutil setuptools wheel packaging ninja numpy==1.26.4
         sh build.sh --config Release --build_dir build/cuda12 --build_shared_lib --parallel \
-                --use_cuda --cuda_version 12.5 --cuda_home $install_dir/cuda12.5 \
-                --cudnn_home $install_dir/cudnn9.4 \
+                --use_cuda --cuda_version 12.6 --cuda_home $install_dir/cuda12.6 \
+                --cudnn_home $install_dir/cudnn9.5 \
                 --build_wheel --skip_tests \
                 --cmake_generator Ninja \
                 --compile_no_warning_as_error \
@@ -203,33 +198,24 @@ build_onnxruntime_gpu_for_profiling()
 
         pip install build/cuda12/Release/dist/onnxruntime_gpu-*-linux_x86_64.whl numpy==1.26.4
     else
-        echo "PyTorch is not installed or No CUDA device found."
+        echo "No CUDA device found."
         exit 1
     fi
-
     popd
 }
 
 # Run profiling with NVTX.
 run_nvtx_profile()
 {
-    pip install nvtx cuda-python==12.5.0
+    pip install nvtx cuda-python==12.6.0
 
     # Only trace one device to avoid huge output file size.
     device_id=0
-
-    # Environment variables
     envs="CUDA_VISIBLE_DEVICES=$device_id,ORT_ENABLE_CUDNN_FLASH_ATTENTION=1,LD_LIBRARY_PATH=$LD_LIBRARY_PATH"
-
-    # For cuda graphs, node activities will be collected and CUDA graphs will not be traced as a whole.
-    # This may cause significant runtime overhead. But it is useful to understand the performance of individual nodes.
     cuda_graph_trace=node
-
-    for engine in ort torch
-    do
-        for component in image_encoder image_decoder
-        do
-            sudo $install_dir/cuda12.5/bin/nsys profile --capture-range=nvtx --nvtx-capture='one_run' \
+    for engine in ort torch; do
+        for component in image_encoder image_decoder; do
+            sudo $install_dir/cuda12.6/bin/nsys profile --capture-range=nvtx --nvtx-capture='one_run' \
                 --gpu-metrics-device $device_id --force-overwrite true \
                 --sample process-tree --backtrace fp --stats true \
                 -t cuda,cudnn,cublas,osrt,nvtx --cuda-memory-usage true --cudabacktrace all \
@@ -246,10 +232,8 @@ run_nvtx_profile()
 }
 
 # Run profiling with PyTorch
-run_torch_profile()
-{
-    for component in image_encoder image_decoder
-    do
+run_torch_profile() {
+    for component in image_encoder image_decoder; do
         $python benchmark_sam2.py --model_type $model --engine torch \
                                   --sam2_dir  $sam2_dir --warm_up 1 --repeats 0 \
                                   --component $component \
@@ -257,50 +241,16 @@ run_torch_profile()
     done
 }
 
-if ! [ -v CONDA_PREFIX ]; then
-    echo "Please activate conda environment before running this script."
-    exit 1
-fi
+run_profilings() {
+    build_onnxruntime_gpu_for_profiling
 
-# Check whether nvidia-smi is available to determine whether to install GPU or CPU version.
-if [ "$cpu_or_gpu" = "gpu" ]; then
-    install_gpu
-else
-    install_cpu
-fi
-
-install_sam2
-
-download_test_image
-
-if ! [ -f sam2_${cpu_or_gpu}.csv ]; then
-    if [ "$cpu_or_gpu" = "gpu" ]; then
-        echo "Running GPU benchmark..."
-        run_gpu 1000
-    else
-        echo "Running CPU benchmark..."
-        run_cpu 100
-    fi
-
-    cat benchmark*.csv > combined_csv
-    awk '!x[$0]++' combined_csv > sam2_${cpu_or_gpu}.csv
-    rm combined_csv
-
-    echo "Benchmarking SAM2 model $model results are saved in sam2_${cpu_or_gpu}.csv"
-else
-    echo "sam2_${cpu_or_gpu}.csv already exists, skipping benchmarking..."
-fi
-
-if [ "$cpu_or_gpu" = "gpu" ]; then
-    echo "Running GPU profiling..."
-    if ! [ -f sam2_fp16_profile_image_decoder_ort_${cpu_or_gpu}.nsys-rep ]; then
-        rm -f *.nsys-rep
-        rm -f *.sqlite
-        build_onnxruntime_gpu_for_profiling
-        run_nvtx_profile
-    else
-        echo "sam2_fp16_profile_image_decoder_ort_${cpu_or_gpu}.nsys-rep already exists, skipping GPU profiling..."
-    fi
+    rm -f *.nsys-rep *.sqlite
+    run_nvtx_profile
 
     run_torch_profile
+}
+
+profiling="${3:-false}"
+if [ "$profiling" = "true" ] &&  [ "$cpu_or_gpu" = "gpu" ]; then
+    run_profilings
 fi