Update to ONNX runtime v1.0

[deliahu]

Description

Here's the commit that reverted the upgrade: 0a106b0

Resolving a series of errors led to adding this to the ONNX GPU Dockerfile:

ENV LD_LIBRARY_PATH "${LD_LIBRARY_PATH}:/usr/lib/x86_64-linux-gnu/:/usr/local/cuda-10.1/targets/x86_64-linux/lib/"
RUN ln -s /usr/lib/x86_64-linux-gnu/libcublas.so.10 /usr/lib/x86_64-linux-gnu/libcublas.so.10.0 && \
    ln -s /usr/lib/x86_64-linux-gnu/libcublasLt.so.10 /usr/lib/x86_64-linux-gnu/libcublasLt.so.10.0 && \
    ln -s /usr/local/cuda-10.1/targets/x86_64-linux/lib/libcudart.so.10.1 /usr/local/cuda-10.1/targets/x86_64-linux/lib/libcudart.so.10.0 && \
    ln -s /usr/local/cuda-10.1/targets/x86_64-linux/lib/libcufft.so.10 /usr/local/cuda-10.1/targets/x86_64-linux/lib/libcufft.so.10.0 && \
    ln -s /usr/local/cuda-10.1/targets/x86_64-linux/lib/libcufftw.so.10 /usr/local/cuda-10.1/targets/x86_64-linux/lib/libcufftw.so.10.0 && \
    ln -s /usr/local/cuda-10.1/targets/x86_64-linux/lib/libcuinj64.so.10.1 /usr/local/cuda-10.1/targets/x86_64-linux/lib/libcuinj64.so.10.0 && \
    ln -s /usr/local/cuda-10.1/targets/x86_64-linux/lib/libcurand.so.10 /usr/local/cuda-10.1/targets/x86_64-linux/lib/libcurand.so.10.0 && \
    ln -s /usr/local/cuda-10.1/targets/x86_64-linux/lib/libcusolver.so.10 /usr/local/cuda-10.1/targets/x86_64-linux/lib/libcusolver.so.10.0 && \
    ln -s /usr/local/cuda-10.1/targets/x86_64-linux/lib/libcusolverMg.so.10 /usr/local/cuda-10.1/targets/x86_64-linux/lib/libcusolverMg.so.10.0 && \
    ln -s /usr/local/cuda-10.1/targets/x86_64-linux/lib/libcusparse.so.10 /usr/local/cuda-10.1/targets/x86_64-linux/lib/libcusparse.so.10.0

Which still resulted in this error:

/usr/local/lib/python3.6/dist-packages/onnxruntime/capi/_pybind_state.py:13: UserWarning: Cannot load onnxruntime.capi. Error: '/usr/lib/x86_64-linux-gnu/libcublas.so.10.0: version `libcublas.so.10.0' not found (required by /usr/local/lib/python3.6/dist-packages/onnxruntime/capi/onnxruntime_pybind11_state.cpython-36m-x86_64-linux-gnu.so)'
  warnings.warn("Cannot load onnxruntime.capi. Error: '{0}'".format(str(e)))
Traceback (most recent call last):
  File "/src/cortex/onnx_serve/api.py", line 23, in <module>
    import onnxruntime as rt
  File "/usr/local/lib/python3.6/dist-packages/onnxruntime/__init__.py", line 12, in <module>
    from onnxruntime.capi._pybind_state import get_all_providers, get_available_providers, get_device, RunOptions, SessionOptions, set_default_logger_severity, NodeArg, ModelMetadata, GraphOptimizationLevel, ExecutionMode
ImportError: cannot import name 'get_all_providers'