diff --git a/benchmarks/nvidia-sdpa/Dockerfile b/benchmarks/nvidia-sdpa/Dockerfile
new file mode 100644
index 0000000..db1d0f1
--- /dev/null
+++ b/benchmarks/nvidia-sdpa/Dockerfile
@@ -0,0 +1,22 @@
+FROM nvcr.io/nvidia/pytorch:25.09-py3
+
+RUN pip install --upgrade pip && \
+    pip install seaborn
+
+RUN apt-get update && \
+    wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/sbsa/cuda-keyring_1.1-1_all.deb && \
+    dpkg -i cuda-keyring_1.1-1_all.deb && \
+    apt-get update && \
+    apt-get -y install cudnn9-cuda-13
+
+RUN pip uninstall -y cudnn
+
+COPY benchmark_bf16_sdpa.py .
+
+COPY benchmark_fp8_sdpa.py .
+
+COPY benchmark_single_sdpa.py .
+
+ENV LD_LIBRARY_PATH=/usr/lib/aarch64-linux-gnu/:$LD_LIBRARY_PATH
+
+WORKDIR /workspace
diff --git a/benchmarks/nvidia-sdpa/README.md b/benchmarks/nvidia-sdpa/README.md
new file mode 100644
index 0000000..eb119fd
--- /dev/null
+++ b/benchmarks/nvidia-sdpa/README.md
@@ -0,0 +1,13 @@
+## Scaled Dot Product Attention Benchmark
+
+The upstream NVIDIA benchmark, which is part of the cudnn-frontend packages (found at https://github.com/NVIDIA/cudnn-frontend/tree/main/benchmark/sdpa_benchmark_training) is using x86_64 specific packages, which doesn't work on GB300 as Grace CPUs are arm (aarch64).
+
+In this repository you'll find a simple fixed Dockerfile which can be used on Nvidia Grace based systems.
+
+Steps:
+1. Clone the repository
+    - `git clone https://github.com/NVIDIA/cudnn-frontend`
+2. Replace the Dockerfile at `cudnn-frontend/benchmark/sdpa_benchmark_training/Dockerfile` with the one from this repo.
+3. Follow the instructions as normal after this
+    - `docker build -t cudnn_attention_benchmark .`
+    - `docker run -it --gpus all --rm -v $(pwd):/workspace cudnn_attention_benchmark`