bump to v0.6.0.post1 (#635)

.github/workflows/publish.yml

@@ -47,15 +47,21 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-          os: ['ubuntu-20.04']
-          python-version: ['3.8', '3.9', '3.10', '3.11', '3.12']
+          os: ['ubuntu-22.04']
+          python-version: ['3.12']
           pytorch-version: ['2.4.0']  # Must be the most recent version that meets requirements-cuda.txt.
           cuda-version: ['12.4', '12.1', '11.8']
 
     steps:
       - name: Checkout
         uses: actions/checkout@v3
 
+      - name: Setup ccache
+        uses: hendrikmuhs/[email protected]
+        with:
+          create-symlink: true
+          key: ${{ github.job }}-${{ matrix.python-version }}-${{ matrix.cuda-version }}
+
       - name: Set up Linux Env
         if: ${{ runner.os == 'Linux' }}
         run: |
@@ -77,7 +83,7 @@ jobs:
       - name: Build wheel
         shell: bash
         env:
-          CMAKE_BUILD_TYPE: Release
+          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 }} ${{ matrix.cuda-version }}
           wheel_name=$(ls dist/*whl | xargs -n 1 basename)

.github/workflows/scripts/build.sh

@@ -7,14 +7,14 @@ cuda_home=/usr/local/cuda-$2
 PATH=${cuda_home}/bin:$PATH
 LD_LIBRARY_PATH=${cuda_home}/lib64:$LD_LIBRARY_PATH
 
-# Limit Ninja's number of processes to 1 to prevent OOM
-# TODO: Can we do 2 jobs?
-export MAX_JOBS=1
-
-export TORCH_CUDA_ARCH_LIST="6.0 6.1 7.0 7.5 8.0 8.6 8.9 9.0+PTX"
 # Install requirements
 $python_executable -m pip install wheel packaging
 $python_executable -m pip install -r requirements-cuda.txt
 
+# Limit the number of parallel jobs to avoid OOM
+export MAX_JOBS=2
+
+export TORCH_CUDA_ARCH_LIST="6.0 6.1 7.0 7.5 8.0 8.6 8.9 9.0+PTX"
+
 # Build
 $python_executable setup.py bdist_wheel --dist-dir=dist

aphrodite/version.py

@@ -11,4 +11,4 @@
     __commit__ = "COMMIT_HASH_PLACEHOLDER"
     __short_commit__ = "SHORT_COMMIT_HASH_PLACEHOLDER"
 
-__version__ = "0.6.0"
+__version__ = "0.6.0.post1"