diff --git a/.github/workflows/fp8_test.yml b/.github/workflows/fp8_test.yml
new file mode 100644
index 0000000000..20cf851aaf
--- /dev/null
+++ b/.github/workflows/fp8_test.yml
@@ -0,0 +1,46 @@
+name: Test fp8
+
+on:
+  push:
+    branches:
+      - main
+  pull_request:
+    branches:
+      - main
+
+concurrency:
+  group: regression_test-${{ github.workflow }}-${{ github.ref == 'refs/heads/main' && github.run_number || github.ref }}
+  cancel-in-progress: true
+
+env:
+  HF_TOKEN: ${{ secrets.HF_TOKEN }}
+
+jobs:
+  test:
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+          - name: SM-89
+            runs-on: amz2023.linux.g6.4xlarge.experimental.nvidia.gpu
+            torch-spec: '--pre torch==2.5.0.dev20240728+cu121 --index-url https://download.pytorch.org/whl/nightly/cu121'
+            gpu-arch-type: "cuda"
+            gpu-arch-version: "12.1"
+
+    uses: pytorch/test-infra/.github/workflows/linux_job.yml@main
+    with:
+      timeout: 60
+      runner: ${{ matrix.runs-on }}
+      gpu-arch-type: ${{ matrix.gpu-arch-type }}
+      gpu-arch-version: ${{ matrix.gpu-arch-version }}
+      script: |
+        conda create -n venv python=3.9 -y
+        conda activate venv
+        echo "::group::Install newer objcopy that supports --set-section-alignment"
+        yum install -y  devtoolset-10-binutils
+        export PATH=/opt/rh/devtoolset-10/root/usr/bin/:$PATH
+        python -m pip install --upgrade pip
+        pip install ${{ matrix.torch-spec }}
+        pip install -r dev-requirements.txt
+        pip install .
+        pytest test/float8