Cached host machines
Hello, I'm reading the docs and trying to understand if caching models is the right approach for my use case.
In the docs, it says "If no cached host machines are available, the system delays starting your workers until the model is downloaded onto the machine where your workers will run". What determines if a cached host machine is available? Can I reasonably rely on one being available? Is this dependent on when my last worker was active?
In the docs, it says "If no cached host machines are available, the system delays starting your workers until the model is downloaded onto the machine where your workers will run". What determines if a cached host machine is available? Can I reasonably rely on one being available? Is this dependent on when my last worker was active?
