Unload model from memory/GPU when idle for set period

This issue was also reported by someone else here: https://github.com/openvinotoolkit/openvino/issues/33665

With the current implementation it is not possible to use the GPU for other workloads while OVMS is running, as it will run out of free vRAM. Other LLM servers approach this by setting a user-defined idle timeout on a model. If no API requests are made to query a specific model for a specific amount of time, that model gets removed from memory. When a new request comes in for the model, it automatically gets loaded into memory again. It would be nice if OVMS had a similar feature.

An explanation of how llama.cpp does it can be found at https://github.com/ggml-org/llama.cpp/tree/master/tools/server#sleeping-on-idle

Start by reading the related OpenVINO issue #33665 and the llama.cpp sleeping-on-idle documentation linked in the report, then trace how OVMS loads and serves models. Define the configurable idle behavior and verify that an idle model is unloaded and automatically available again when a new request arrives.