[workflow] added nightly release to pypi (#2403)

.github/workflows/release_nightly.yml

@@ -1,73 +1,29 @@
-name: Release bdist wheel for Nightly versions
+name: Publish Nightly Version to PyPI
 
 on:
-  schedule:
-    # run at 00:00 of every Sunday
-    - cron:  '0 0 * * 6'
   workflow_dispatch:
+  schedule:
+    - cron:  '0 0 * * 6' # release on every Sunday 00:00 UTC time
 
 jobs:
-  matrix_preparation:
-    name: Prepare Container List
+  build-n-publish:
+    if: github.event_name == 'workflow_dispatch' || github.repository == 'hpcaitech/ColossalAI'
+    name: Build and publish Python 🐍 distributions 📦 to PyPI
     runs-on: ubuntu-latest
-    outputs:
-      matrix: ${{ steps.set-matrix.outputs.matrix }}
+    timeout-minutes: 20
     steps:
-    - id: set-matrix
-      run: |
-        matrix="[\"hpcaitech/cuda-conda:11.3\", \"hpcaitech/cuda-conda:10.2\"]"
-        echo $matrix
-        echo "::set-output name=matrix::{\"container\":$(echo $matrix)}"
+    - uses: actions/checkout@v2
 
-  build:
-    name: Release bdist wheels
-    needs: matrix_preparation
-    if: github.repository == 'hpcaitech/ColossalAI' && contains(fromJson('["FrankLeeeee", "ver217", "feifeibear", "kurisusnowdeng"]'), github.actor)
-    runs-on: [self-hosted, gpu]
-    strategy:
-      fail-fast: false
-      matrix: ${{fromJson(needs.matrix_preparation.outputs.matrix)}}
-    container:
-      image: ${{ matrix.container }}
-      options: --gpus all --rm
-    steps:
-      - uses: actions/checkout@v2
-        with:
-          fetch-depth: 0
-      # cub is for cuda 10.2
-      - name: Copy scripts and checkout
-        run: |
-          cp -r ./.github/workflows/scripts/* ./
-          ln -s /github/home/pip_wheels ./pip_wheels
-          wget https://github.com/NVIDIA/cub/archive/refs/tags/1.8.0.zip
-          unzip 1.8.0.zip
-      - name: Build bdist wheel
-        run: |
-          pip install beautifulsoup4 requests packaging
-          python ./build_colossalai_wheel.py --nightly
-      - name: 🚀 Deploy
-        uses: garygrossgarten/github-action-scp@release
-        with:
-          local: all_dist
-          remote: ${{ secrets.PRIVATE_PYPI_NIGHTLY_DIR }}
-          host: ${{ secrets.PRIVATE_PYPI_HOST }}
-          username: ${{ secrets.PRIVATE_PYPI_USER }}
-          password: ${{ secrets.PRIVATE_PYPI_PASSWD }}
-  remove_old_build:
-    name: Remove old nightly build
-    runs-on: ubuntu-latest
-    needs: build
-    steps:
-      - name: executing remote ssh commands using password
-        uses: appleboy/ssh-action@master
-        env:
-          BUILD_DIR: ${{ secrets.PRIVATE_PYPI_NIGHTLY_DIR }}
-        with:
-          host: ${{ secrets.PRIVATE_PYPI_HOST }}
-          username: ${{ secrets.PRIVATE_PYPI_USER }}
-          password: ${{ secrets.PRIVATE_PYPI_PASSWD }}
-          envs: BUILD_DIR
-          script: |
-            cd $BUILD_DIR
-            find . -type f -mtime +0 -exec rm -f {} +
-          script_stop: true
+    - uses: actions/setup-python@v2
+      with:
+        python-version: '3.8.14'
+
+    - run: NIGHTLY=1 python setup.py sdist build
+
+    # publish to PyPI if executed on the main branch
+    - name: Publish package to PyPI
+      uses: pypa/gh-action-pypi-publish@release/v1
+      with:
+        user: __token__
+        password: ${{ secrets.PYPI_API_TOKEN }}
+        verbose: true

setup.py

@@ -1,5 +1,6 @@
 import os
 import re
+from datetime import datetime
 
 from setuptools import find_packages, setup
 
@@ -20,18 +21,22 @@ except ImportError:
     TORCH_AVAILABLE = False
     CUDA_HOME = None
 
-
 # ninja build does not work unless include_dirs are abs path
 this_dir = os.path.dirname(os.path.abspath(__file__))
 build_cuda_ext = False
 ext_modules = []
+is_nightly = int(os.environ.get('NIGHTLY', '0')) == 1
 
 if int(os.environ.get('CUDA_EXT', '0')) == 1:
     if not TORCH_AVAILABLE:
-        raise ModuleNotFoundError("PyTorch is not found while CUDA_EXT=1. You need to install PyTorch first in order to build CUDA extensions")
+        raise ModuleNotFoundError(
+            "PyTorch is not found while CUDA_EXT=1. You need to install PyTorch first in order to build CUDA extensions"
+        )
 
     if not CUDA_HOME:
-        raise RuntimeError("CUDA_HOME is not found while CUDA_EXT=1. You need to export CUDA_HOME environment vairable or install CUDA Toolkit first in order to build CUDA extensions")
+        raise RuntimeError(
+            "CUDA_HOME is not found while CUDA_EXT=1. You need to export CUDA_HOME environment vairable or install CUDA Toolkit first in order to build CUDA extensions"
+        )
 
     build_cuda_ext = True
 
@@ -139,8 +144,16 @@ if build_cuda_ext:
         print(f'===== Building Extension {name} =====')
         ext_modules.append(builder_cls().builder())
 
-setup(name='colossalai',
-      version=get_version(),
+if is_nightly:
+    # use date as the nightly version
+    version = datetime.today().strftime('%Y.%m.%d')
+    package_name = 'colossalai-nightly'
+else:
+    version = get_version()
+    package_name = 'colossalai'
+
+setup(name=package_name,
+      version=version,
       packages=find_packages(exclude=(
           'benchmark',
           'docker',
@@ -179,4 +192,9 @@ setup(name='colossalai',
           'Topic :: Scientific/Engineering :: Artificial Intelligence',
           'Topic :: System :: Distributed Computing',
       ],
-      package_data={'colossalai': ['_C/*.pyi', 'kernel/cuda_native/csrc/*', 'kernel/cuda_native/csrc/kernel/*', 'kernel/cuda_native/csrc/kernels/include/*']})
+      package_data={
+          'colossalai': [
+              '_C/*.pyi', 'kernel/cuda_native/csrc/*', 'kernel/cuda_native/csrc/kernel/*',
+              'kernel/cuda_native/csrc/kernels/include/*'
+          ]
+      })