ci: add manylinux wheel generation and upload in Linux self-hosted build

- Add auditwheel repair step to generate manylinux-compatible wheels
- Verify manylinux wheel installation and package imports
- Upload repaired wheels to GitHub release with --clobber flag

.github/workflows/_build_linux_self_host.yml

@@ -148,6 +148,34 @@ jobs:
           # Upload the release asset using GitHub CLI
           gh release upload "$tag_name" "$wheel_path" --clobber
 
+      - name: Apply auditwheel repair
+        continue-on-error: true
+        run: |
+          pip install auditwheel
+          auditwheel show flash-attention/dist/${{ steps.build_wheels.outputs.WHEEL_NAME }}
+          auditwheel repair flash-attention/dist/${{ steps.build_wheels.outputs.WHEEL_NAME }} -w flash-attention/dist_manylinux
+          wheel_name=$(basename $(ls flash-attention/dist_manylinux/*.whl | head -n 1))
+          echo "WHEEL_NAME_MANYLINUX=$wheel_name" >> $GITHUB_OUTPUT
+
+      - name: Apply auditwheel repair
+        if: ${{ inputs.is-upload }}
+        continue-on-error: true
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        run: |
+          pip uninstall -y flash-attn > /dev/null 2>&1
+          pip install --no-cache-dir flash-attention/dist_manylinux/${{ steps.build_wheels.outputs.WHEEL_NAME_MANYLINUX }}
+          python -c "import flash_attn; print(flash_attn.__version__)"
+
+          wheel_path_manylinux="flash-attention/dist_manylinux/${{ steps.build_wheels.outputs.WHEEL_NAME_MANYLINUX }}"
+          if [ ! -f "$wheel_path_manylinux" ]; then
+            echo "Error: Wheel file not found at $wheel_path_manylinux"
+            exit 1
+          fi
+
+          # Upload the release asset using GitHub CLI
+          gh release upload "$tag_name" "$wheel_path_manylinux" --clobber
+
       - name: Clean up
         shell: bash
         if: always()