build:mkl_aarch64_threadpool --define=build_with_mkl_aarch64=true
build:mkl_aarch64_threadpool -c opt

# CUDA: This config refers to building CUDA op kernels with nvcc.
build:cuda --repo_env TF_NEED_CUDA=1
build:cuda --crosstool_top=@local_config_cuda//crosstool:toolchain
build:cuda --@local_config_cuda//:enable_cuda

# CUDA: This config refers to building CUDA op kernels with clang.
build:cuda_clang --config=cuda

*   Update `tf.keras` to the Keras 2.1.6 API.
*   Added
    [`tf.keras.layers.CuDNNGRU`](https://www.tensorflow.org/versions/r1.9/api_docs/python/tf/keras/layers/CuDNNGRU)
    and
    [`tf.keras.layers.CuDNNLSTM`](https://www.tensorflow.org/versions/r1.9/api_docs/python/tf/keras/layers/CuDNNLSTM)
    layers.

TF_CAPI_EXPORT extern bool TFE_ExecutorIsAsync(TFE_Executor*);

// Causes the calling thread to block till all ops dispatched in this executor
// have been executed. Note that "execution" here refers to kernel execution /
// scheduling of copies, etc. Similar to sync execution, it doesn't guarantee
// that lower level device queues (like GPU streams) have been flushed.
//