diff --git a/.github/workflows/publish.yml b/.github/workflows/publish.yml
index f959a1cacf866..830a2fff4dbe4 100644
--- a/.github/workflows/publish.yml
+++ b/.github/workflows/publish.yml
@@ -16,7 +16,9 @@ jobs:
   release:
     # Retrieve tag and create release
     name: Create Release
-    runs-on: ubuntu-latest
+    runs-on: self-hosted
+    container:
+      image: rocm/pytorch:rocm6.2_ubuntu20.04_py3.9_pytorch_release_2.3.0
     outputs:
       upload_url: ${{ steps.create_release.outputs.upload_url }}
     steps:
@@ -41,57 +43,39 @@ jobs:
 
   wheel:
     name: Build Wheel
-    runs-on: ${{ matrix.os }}
+    runs-on: self-hosted
+    container:
+      image: rocm/pytorch:rocm6.2_ubuntu20.04_py3.9_pytorch_release_2.3.0
     needs: release
 
     strategy:
       fail-fast: false
-      matrix:
-          os: ['ubuntu-20.04']
-          python-version: ['3.8', '3.9', '3.10', '3.11', '3.12']
-          pytorch-version: ['2.4.0']  # Must be the most recent version that meets requirements-cuda.txt.
-          cuda-version: ['11.8', '12.1']
 
     steps:
-      - name: Checkout
-        uses: actions/checkout@eef61447b9ff4aafe5dcd4e0bbf5d482be7e7871 # v4.2.1
-
-      - name: Setup ccache
-        uses: hendrikmuhs/ccache-action@ed74d11c0b343532753ecead8a951bb09bb34bc9 # v1.2.14
-        with:
-          create-symlink: true
-          key: ${{ github.job }}-${{ matrix.python-version }}-${{ matrix.cuda-version }}
-
-      - name: Set up Linux Env
-        if: ${{ runner.os == 'Linux' }}
-        run: |
-          bash -x .github/workflows/scripts/env.sh
-
-      - name: Set up Python
-        uses: actions/setup-python@f677139bbe7f9c59b41e40162b753c062f5d49a3 # v5.2.0
-        with:
-            python-version: ${{ matrix.python-version }}
-
-      - name: Install CUDA ${{ matrix.cuda-version }}
+      - name: Prepare
         run: |
-          bash -x .github/workflows/scripts/cuda-install.sh ${{ matrix.cuda-version }} ${{ matrix.os }}
+          pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/rocm6.2
+          pip3 install -U triton
 
-      - name: Install PyTorch ${{ matrix.pytorch-version }} with CUDA ${{ matrix.cuda-version }}
-        run: |
-          bash -x .github/workflows/scripts/pytorch-install.sh ${{ matrix.python-version }} ${{ matrix.pytorch-version }} ${{ matrix.cuda-version }}
+      - name: Checkout
+        uses: actions/checkout@eef61447b9ff4aafe5dcd4e0bbf5d482be7e7871 # v4.2.1
 
       - name: Build wheel
         shell: bash
         env:
           CMAKE_BUILD_TYPE: Release # do not compile with debug symbol to reduce wheel size
         run: |
-          bash -x .github/workflows/scripts/build.sh ${{ matrix.python-version }} ${{ matrix.cuda-version }}
+          bash -x .github/workflows/scripts/build.sh
           wheel_name=$(find dist -name "*whl" -print0 | xargs -0 -n 1 basename)
           asset_name=${wheel_name//"linux"/"manylinux1"}
+          gradlib_wheel_name=$(find gradlib/dist -name "*whl" -print0 | xargs -0 -n 1 basename)
+          gradlib_asset_name=${gradlib_wheel_name//"linux"/"manylinux1"}
           echo "wheel_name=${wheel_name}" >> "$GITHUB_ENV"
           echo "asset_name=${asset_name}" >> "$GITHUB_ENV"
+          echo "gradlib_wheel_name=${gradlib_wheel_name}" >> "$GITHUB_ENV"
+          echo "gradlib_asset_name=${gradlib_asset_name}" >> "$GITHUB_ENV"
 
-      - name: Upload Release Asset
+      - name: Upload vllm Release Asset
         uses: actions/upload-release-asset@e8f9f06c4b078e705bd2ea027f0926603fc9b4d5 # v1.0.2
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
@@ -100,11 +84,13 @@ jobs:
           asset_path: ./dist/${{ env.wheel_name }}
           asset_name: ${{ env.asset_name }}
           asset_content_type: application/*
+      - name: Upload gradlib Release Asset
+        uses: actions/upload-release-asset@e8f9f06c4b078e705bd2ea027f0926603fc9b4d5 # v1.0.2
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        with:
+          upload_url: ${{ needs.release.outputs.upload_url }}
+          asset_path: ./gradlib/dist/${{ env.gradlib_wheel_name }}
+          asset_name: ${{ env.gradlib_asset_name }}
+          asset_content_type: application/*
 
-      # (Danielkinz): This last step will publish the .whl to pypi. Warning: untested
-      # - name: Publish package
-      #   uses: pypa/gh-action-pypi-publish@release/v1.8
-      #   with:
-      #     repository-url: https://test.pypi.org/legacy/
-      #     password: ${{ secrets.PYPI_API_TOKEN }}
-      #     skip-existing: true
diff --git a/.github/workflows/scripts/build.sh b/.github/workflows/scripts/build.sh
index 122e4e101e201..01131807d2021 100644
--- a/.github/workflows/scripts/build.sh
+++ b/.github/workflows/scripts/build.sh
@@ -1,23 +1,23 @@
 #!/bin/bash
 set -eux
 
-python_executable=python$1
-cuda_home=/usr/local/cuda-$2
+python_executable=python3
 
 # Update paths
-PATH=${cuda_home}/bin:$PATH
-LD_LIBRARY_PATH=${cuda_home}/lib64:$LD_LIBRARY_PATH
-
 # Install requirements
-$python_executable -m pip install -r requirements-build.txt -r requirements-cuda.txt
+$python_executable -m pip install -r requirements-rocm.txt
 
 # Limit the number of parallel jobs to avoid OOM
 export MAX_JOBS=1
 # Make sure release wheels are built for the following architectures
-export TORCH_CUDA_ARCH_LIST="7.0 7.5 8.0 8.6 8.9 9.0+PTX"
-export VLLM_FA_CMAKE_GPU_ARCHES="80-real;90-real"
+export PYTORCH_ROCM_ARCH="gfx90a;gfx942"
+
+rm -f $(which sccache)
 
-bash tools/check_repo.sh
+export MAX_JOBS=32
 
 # Build
 $python_executable setup.py bdist_wheel --dist-dir=dist
+cd gradlib
+$python_executable setup.py bdist_wheel --dist-dir=dist
+cd ..
\ No newline at end of file