build:cuda_clang --config=cuda
# Enable TensorRT optimizations https://developer.nvidia.com/tensorrt
build:cuda_clang --config=tensorrt
build:cuda_clang --action_env=TF_CUDA_CLANG="1"
build:cuda_clang --@local_config_cuda//:cuda_compiler=clang
# Select supported compute capabilities (supported graphics cards).
# This is the same as the official TensorFlow builds.
# See https://developer.nvidia.com/cuda-gpus#compute

    ask_cuda_compute_capabilities = (
        'Please specify a list of comma-separated CUDA compute capabilities '
        'you want to build with.\nYou can find the compute capability of your '
        'device at: https://developer.nvidia.com/cuda-gpus. Each capability '
        'can be specified as "x.y" or "compute_xy" to include both virtual and'
        ' binary GPU code, or as "sm_xy" to only include the binary '

        `tf.distribute.experimental.MultiWorkerMirroredStrategy`
    *   Update NVIDIA `NCCL` to `2.5.7-1` for better performance and performance
        tuning. Please see
        [nccl developer guide](https://docs.nvidia.com/deeplearning/sdk/nccl-developer-guide/docs/env.html)
        for more information on this.
    *   Support gradient `allreduce` in `float16`. See this