Crate autodep

Modules

• config
  Autodep configuration – can eventually be lazy_static parsed from a config file
• manager
  The manager (worker manager, resource allocator, allocator) is responsible for interfacing with a set of workers. The manager starts and stops workers, and forwards inference requests
• rpc
  The worker’s RPC server
• server
• torch
  Code for loading and running (trained) PyTorch models
• util
  Network utility functions
• worker
  An inference worker listens for requests from the Manager and computes model inference in an isolated environment