add support for automatically unloading a model (#10) (#14)

* Make starting upstream process on-demand (#10)
* Add automatic unload of model after TTL is reached
* add `ttl` configuration parameter to models in seconds, default is 0 (never unload)

README.md

@@ -39,6 +39,11 @@ models:
     # until the server is ready
     checkEndpoint: /custom-endpoint
 
+    # automatically unload the model after 10 seconds
+    # ttl values must be a value greater than 0
+    # default: 0 = never unload model
+    ttl: 5
+
   "qwen":
     # environment variables to pass to the command
     env: