This PR allows a single llama-swap to be the central proxy for models served by other inference servers. The peer servers can be another llama-swap or any API that supports the /v1/* inference endpoint.
Updates: #433, #299Closes: #296
introduces a new configuration option logTimeFormat that allows customizing the timestamp in log messages using golang's built in time format constants. The default remains no timestamp.
Benson Wong
Ryan Steed