[docker] updated Dockerfile and release workflow (#2410)

.github/workflows/release_docker.yml

@@ -18,23 +18,17 @@ jobs:
         with:
           fetch-depth: 0
       - name: Build Docker
+        id: build
         run: |
           version=$(cat version.txt)
-          docker build --build-arg http_proxy=http://172.17.0.1:7890 --build-arg https_proxy=http://172.17.0.1:7890 -t hpcaitech/colossalai:$version ./docker
+          tag=hpcaitech/colossalai:$version
+          docker build --build-arg http_proxy=http://172.17.0.1:7890 --build-arg https_proxy=http://172.17.0.1:7890 -t $tag ./docker
+          echo "tag=${tag}" >> $GITHUB_OUTPUT
       - name: Log in to Docker Hub
         uses: docker/login-action@f054a8b539a109f9f41c372932f1ae047eff08c9
         with:
           username: ${{ secrets.DOCKER_USERNAME }}
           password: ${{ secrets.DOCKER_PASSWORD }}
-      - name: Extract metadata (tags, labels) for Docker
+      - name: Push Docker image
-        id: meta
+        run: |
-        uses: docker/metadata-action@98669ae865ea3cffbcbaa878cf57c20bbf1c6c38
+          docker push ${{ steps.build.outputs.tag }}
-        with:
-          images: hpcaitech/colossalai
-      - name: Build and push Docker image
-        uses: docker/build-push-action@ad44023a93711e3deb337508980b4b5e9bcdc5dc
-        with:
-          context: .
-          push: true
-          tags: ${{ steps.meta.outputs.tags }}
-          labels: ${{ steps.meta.outputs.labels }}

docker/Dockerfile

@@ -1,17 +1,18 @@
 FROM hpcaitech/cuda-conda:11.3
 
 # install torch
-RUN conda install pytorch torchvision torchaudio cudatoolkit=11.3 -c pytorch
+RUN conda install pytorch==1.12.1 torchvision==0.13.1 torchaudio==0.12.1 cudatoolkit=11.3 -c pytorch
 
 # install apex
 RUN git clone https://github.com/NVIDIA/apex && \
     cd apex && \
+    pip install packaging && \
     pip install -v --disable-pip-version-check --no-cache-dir --global-option="--cpp_ext" --global-option="--cuda_ext" --global-option="--fast_layer_norm" ./
 
 # install colossalai
 RUN git clone https://github.com/hpcaitech/ColossalAI.git \
     && cd ./ColossalAI \
-    && pip install -v --no-cache-dir .
+    && CUDA_EXT=1 pip install -v --no-cache-dir .
 
 # install titans
 RUN pip install --no-cache-dir titans