feat(ci): update ci and readme

.github/workflows/ci.yml

@@ -23,12 +23,13 @@ jobs:
     runs-on: self-hosted
     needs: [check-commit]
     container:
-      image: localhost:5000/megengine-ci:latest
+      image: localhost:5000/megengine-ci:v1
     steps:
       - name: Checkout MegEngine
         uses: actions/checkout@v2
       - name: Checkout submodules
         run: |
+          apt update&&apt install ninja-build
           ./third_party/prepare.sh
           ./third_party/install-mkl.sh
       - name: Build MegEngine
@@ -46,9 +47,9 @@ jobs:
     runs-on: self-hosted
     needs: [check-commit]
     container:
-      image: localhost:5000/megengine-ci:latest
+      image: localhost:5000/megengine-ci:v1
       volumes:
-        - /usr/local/cuda-10.1-libs:/usr/local/cuda-10.1-libs
+        - /usr/local/cuda-10.1-cudnn-7.6.3-trt-6.0.1.5-libs:/usr/local/cuda-10.1-cudnn-7.6.3-trt-6.0.1.5-libs
       options: --gpus all --shm-size 1g
       env:
         NCCL_LAUNCH_MODE: PARALLEL
@@ -57,6 +58,7 @@ jobs:
         uses: actions/checkout@v2
       - name: Checkout submodules
         run: |
+          apt update&&apt install ninja-build
           ./third_party/prepare.sh
           ./third_party/install-mkl.sh
       - name: Build MegEngine
@@ -72,8 +74,10 @@ jobs:
         run: ./ci/run_cpp_test.sh cuda
   auto-merge:
     if: ${{ github.ref == 'refs/heads/try-import' }}
-    runs-on: ubuntu-latest
+    runs-on: self-hosted
     needs: [cpu-test, gpu-test]
+    container:
+      image: localhost:5000/megengine-ci:v1
     steps:
       - name: Checkout MegEngine
         uses: actions/checkout@v2

README.md

@@ -12,7 +12,7 @@ MegEngine is a fast, scalable and easy-to-use deep learning framework, with auto
 
 ## Installation
 
-**NOTE:** MegEngine now supports Python installation on Linux-64bit/Windows-64bit/MacOS(CPU-Only)-10.14+ platforms with Python from 3.5 to 3.8. On Windows 10 you can either install the Linux distribution through [Windows Subsystem for Linux (WSL)](https://docs.microsoft.com/en-us/windows/wsl) or install the Windows distribution directly. Many other platforms are supported for inference.
+**NOTE:** MegEngine now supports Python installation on Linux-64bit/Windows-64bit/MacOS(CPU-Only)-10.14+/Android 7+(CPU-Only) platforms with Python from 3.5 to 3.8. On Windows 10 you can either install the Linux distribution through [Windows Subsystem for Linux (WSL)](https://docs.microsoft.com/en-us/windows/wsl) or install the Windows distribution directly. Many other platforms are supported for inference.
 
 ### Binaries
 

README_CN.md

@@ -13,7 +13,7 @@ MegEngine 是一个快速、可拓展、易于使用且支持自动求导的深
 
 ## 安装说明
 
-**注意:** MegEngine 现在支持在 Linux-64bit/Windows-64bit/macos-10.14及其以上 (MacOS只支持cpu) 等平台上安装 Python 包，支持Python3.5 到 Python3.8。对于 Windows 10 用户，可以通过安装 [Windows Subsystem for Linux (WSL)](https://docs.microsoft.com/en-us/windows/wsl) 进行体验，同时我们也原生支持Windows。MegEngine 也支持在很多其它平台上进行推理运算。
+**注意:** MegEngine 现在支持在 Linux-64bit/Windows-64bit/macos-10.14/Android 7+ 及其以上 (MacOS/Android只支持cpu) 等平台上安装 Python 包，支持Python3.5 到 Python3.8。对于 Windows 10 用户，可以通过安装 [Windows Subsystem for Linux (WSL)](https://docs.microsoft.com/en-us/windows/wsl) 进行体验，同时我们也原生支持Windows。MegEngine 也支持在很多其它平台上进行推理运算。
 
 ### 通过包管理器安装
 
@@ -26,8 +26,8 @@ python3 -m pip install megengine -f https://megengine.org.cn/whl/mge.html
 
 ## 通过源码编译安装
 
-* CMake编译细节请参考 [BUILD_README.md](scripts/cmake-build/BUILD_README.md)
-* Python绑定编译细节请参考 [BUILD_PYTHON_WHL_README.md](scripts/whl/BUILD_PYTHON_WHL_README.md)
+* CMake 编译细节请参考 [BUILD_README.md](scripts/cmake-build/BUILD_README.md)
+* Python 绑定编译细节请参考 [BUILD_PYTHON_WHL_README.md](scripts/whl/BUILD_PYTHON_WHL_README.md)
 
 ## 如何参与贡献
 

ci/cmake.sh

@@ -27,7 +27,8 @@ function build() {
             -DMGE_WITH_DISTRIBUTED=${DMGE_WITH_DISTRIBUTED} \
             -DMGE_WITH_CUDA=${DMGE_WITH_CUDA} \
             -DMGE_WITH_TEST=ON \
-            -DCMAKE_BUILD_TYPE=RelWithDebInfo
+            -DCMAKE_BUILD_TYPE=RelWithDebInfo \
+            -DMGE_WITH_CUSTOM_OP=ON
         make -j$(($(nproc) * 2)) -I ${build_dir}
         make develop
     popd >/dev/null

ci/docker_env/Dockerfile

@@ -24,17 +24,27 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
     swig \
     vim \
     wget \
+    libgl1-mesa-glx \
+    libsm6 \
+    libxext6 \
     zlib1g-dev \
     # GitLab Runner need Git 2.18 or higher to create a local Git repository
     && add-apt-repository ppa:git-core/ppa -y && apt-get install --no-install-recommends -y git \
     && rm -rf /var/lib/apt/lists/*
 
-RUN cd /tmp ; wget https://cmake.org/files/v3.14/cmake-3.14.4.tar.gz;tar -xzvf cmake-3.14.4.tar.gz;cd cmake-3.14.4;./configure; make -j32; make install
+RUN cd /tmp ; wget https://cmake.org/files/v3.15/cmake-3.15.2.tar.gz;tar -xzvf cmake-3.15.2.tar.gz;cd cmake-3.15.2;./configure; make -j32; make install
 
 RUN git lfs install
 
-ENV PATH=${PATH}:/usr/local/cuda/bin \
-  LIBRARY_PATH=${LIBRARY_PATH}:/usr/local/cuda/lib:/usr/local/cuda/lib64:/usr/local/cuda/lib/stubs:/usr/local/cuda/lib64/stubs:/usr/local/cuda-10.1-libs/cudnn-v7.6.0/lib:/usr/local/cuda-10.1-libs/cudnn-v7.6.0/lib64:/usr/local/cuda-10.1-libs/TensorRT-5.1.5.0/lib:/usr/local/cuda-10.1-libs/TensorRT-5.1.5.0/lib64 \
-  LD_LIBRARY_PATH=/usr/local/nvidia/lib:/usr/local/nvidia/lib64:/usr/local/nvidia/lib:/usr/local/nvidia/lib64:/usr/local/cuda-10.1-libs/cudnn-v7.6.0/lib:/usr/local/cuda-10.1-libs/cudnn-v7.6.0/lib64:/usr/local/cuda-10.1-libs/TensorRT-5.1.5.0/lib:/usr/local/cuda-10.1-libs/TensorRT-5.1.5.0/lib64:/tmp/build/cuda/dnn/cuda-stub/libcuda.so \
-  CPATH=${CPATH}:/usr/local/cuda/include:/usr/local/cuda-10.1-libs/cudnn-v7.6.0/include:/usr/local/cuda-10.1-libs/TensorRT-5.1.5.0/include \
-  CUDA_BIN_PATH=/usr/local/cuda
+RUN pip3 install --upgrade pip
+
+# TODO: set following envs in github environment.
+ENV CUDA_ROOT_DIR=/usr/local/cuda-10.1-cudnn-7.6.3-trt-6.0.1.5-libs/cuda-10.1 \
+  TRT_ROOT_DIR=/usr/local/cuda-10.1-cudnn-7.6.3-trt-6.0.1.5-libs/TensorRT-6.0.1.5 \
+  TENSORRT_ROOT_DIR=${TRT_ROOT_DIR} \
+  CUDNN_ROOT_DIR=/usr/local/cuda-10.1-cudnn-7.6.3-trt-6.0.1.5-libs/cudnn-v7.6.3 \
+  PATH=/usr/bin:${CUDA_ROOT_DIR}/bin:${CUDA_ROOT_DIR}/nsight-compute-2019.4.0:$PATH \
+  LIBRARY_PATH=${LIBRARY_PATH}:/usr/local/cuda-10.1-cudnn-7.6.3-trt-6.0.1.5-libs/cuda-10.1/lib:/usr/local/cuda-10.1-cudnn-7.6.3-trt-6.0.1.5-libs/cuda-10.1/lib64:/usr/local/cuda-10.1-cudnn-7.6.3-trt-6.0.1.5-libs/cuda-10.1/lib/stubs:/usr/local/cuda-10.1-cudnn-7.6.3-trt-6.0.1.5-libs/cuda-10.1/lib64/stubs:/usr/local/cuda-10.1-cudnn-7.6.3-trt-6.0.1.5-libs/cudnn-v7.6.3/lib:/usr/local/cuda-10.1-cudnn-7.6.3-trt-6.0.1.5-libs/cudnn-v7.6.3/lib64:/usr/local/cuda-10.1-cudnn-7.6.3-trt-6.0.1.5-libs/TensorRT-6.0.1.5/lib:/usr/local/cuda-10.1-cudnn-7.6.3-trt-6.0.1.5-libs/TensorRT-6.0.1.5/lib64 \
+  LD_LIBRARY_PATH=/usr/local/nvidia/lib:/usr/local/nvidia/lib64:/usr/local/nvidia/lib:/usr/local/nvidia/lib64:/usr/local/cuda-10.1-cudnn-7.6.3-trt-6.0.1.5-libs/cudnn-v7.6.3/lib:/usr/local/cuda-10.1-cudnn-7.6.3-trt-6.0.1.5-libs/cudnn-v7.6.3/lib64:/usr/local/cuda-10.1-cudnn-7.6.3-trt-6.0.1.5-libs/TensorRT-6.0.1.5/lib:/usr/local/cuda-10.1-cudnn-7.6.3-trt-6.0.1.5-libs/TensorRT-6.0.1.5/lib64  \
+  CPATH=${CPATH}:/usr/local/cuda-10.1-cudnn-7.6.3-trt-6.0.1.5-libs/cuda-10.1/include:/usr/local/cuda-10.1-cudnn-7.6.3-trt-6.0.1.5-libs/cudnn-v7.6.3/include:/usr/local/cuda-10.1-cudnn-7.6.3-trt-6.0.1.5-libs/TensorRT-6.0.1.5/include \
+  CUDA_BIN_PATH=/usr/local/cuda-10.1-cudnn-7.6.3-trt-6.0.1.5-libs/cuda-10.1