diff --git a/.github/workflows/publish.yml b/.github/workflows/publish.yml
index ead7ff04b..cfc1aa337 100644
--- a/.github/workflows/publish.yml
+++ b/.github/workflows/publish.yml
@@ -43,14 +43,14 @@ jobs:
           # Using ubuntu-20.04 instead of 22.04 for more compatibility (glibc). Ideally we'd use the
           # manylinux docker image, but I haven't figured out how to install CUDA on manylinux.
           os: [ubuntu-20.04]
-          python-version: ['3.8', '3.9', '3.10', '3.11', '3.12']
-          torch-version: ['2.0.1', '2.1.2', '2.2.2', '2.3.1', '2.4.0']
-          cuda-version: ['11.8.0', '12.3.2']
+          python-version: ['3.9', '3.10']
+          torch-version: ['2.4.0']
+          cuda-version: ['11.8.0']
           # We need separate wheels that either uses C++11 ABI (-D_GLIBCXX_USE_CXX11_ABI) or not.
           # Pytorch wheels currently don't use it, but nvcr images have Pytorch compiled with C++11 ABI.
           # Without this we get import error (undefined symbol: _ZN3c105ErrorC2ENS_14SourceLocationESs)
           # when building without C++11 ABI and using it on nvcr images.
-          cxx11_abi: ['FALSE', 'TRUE']
+          cxx11_abi: ['FALSE']
           exclude:
             # see https://github.com/pytorch/pytorch/blob/main/RELEASE.md#release-compatibility-matrix
             # Pytorch < 2.2 does not support Python 3.12
@@ -179,34 +179,34 @@ jobs:
           asset_name: ${{env.wheel_name}}
           asset_content_type: application/*
 
-  publish_package:
-    name: Publish package
-    needs: [build_wheels]
-
-    runs-on: ubuntu-latest
-
-    steps:
-      - uses: actions/checkout@v3
-
-      - uses: actions/setup-python@v4
-        with:
-          python-version: '3.10'
-
-      - name: Install dependencies
-        run: |
-          pip install ninja packaging setuptools wheel twine
-          # We don't want to download anything CUDA-related here
-          pip install torch --index-url https://download.pytorch.org/whl/cpu
-
-      - name: Build core package
-        env:
-          FLASH_ATTENTION_SKIP_CUDA_BUILD: "TRUE"
-        run: |
-          python setup.py sdist --dist-dir=dist
-
-      - name: Deploy
-        env:
-          TWINE_USERNAME: "__token__"
-          TWINE_PASSWORD: ${{ secrets.PYPI_API_TOKEN }}
-        run: |
-          python -m twine upload dist/*
+  # publish_package:
+  #   name: Publish package
+  #   needs: [build_wheels]
+
+  #   runs-on: ubuntu-latest
+
+  #   steps:
+  #     - uses: actions/checkout@v3
+
+  #     - uses: actions/setup-python@v4
+  #       with:
+  #         python-version: '3.10'
+
+  #     - name: Install dependencies
+  #       run: |
+  #         pip install ninja packaging setuptools wheel twine
+  #         # We don't want to download anything CUDA-related here
+  #         pip install torch --index-url https://download.pytorch.org/whl/cpu
+
+  #     - name: Build core package
+  #       env:
+  #         FLASH_ATTENTION_SKIP_CUDA_BUILD: "TRUE"
+  #       run: |
+  #         python setup.py sdist --dist-dir=dist
+
+  #     - name: Deploy
+  #       env:
+  #         TWINE_USERNAME: "__token__"
+  #         TWINE_PASSWORD: ${{ secrets.PYPI_API_TOKEN }}
+  #       run: |
+  #         python -m twine upload dist/*