tff.backends.native.create_async_local_cpp_execution_context

Returns an execution context backed by C++ runtime.

tff.backends.native.create_async_local_cpp_execution_context(
    default_num_clients: int = 0,
    max_concurrent_computation_calls: int = -1,
    stream_structs: bool = False
) -> tff.framework.AsyncExecutionContext

This execution context starts a C++ worker assumed to be at path binary_path, serving on port, and constructs a Python remote execution context to talk to this worker.

default_num_clients The number of clients to use as the default cardinality, if thus number cannot be inferred by the arguments of a computation.
max_concurrent_computation_calls The maximum number of concurrent calls to a single computation in the C++ runtime. If None, there is no limit.
stream_structs The flag to enable decomposing and streaming struct values.

RuntimeError If an internal C++ worker binary can not be found.