Add Peer Model Support (#438)

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, #299
Closes: #296

proxy/proxymanager_api.go

@@ -18,6 +18,7 @@ type Model struct {
 	Description string `json:"description"`
 	State       string `json:"state"`
 	Unlisted    bool   `json:"unlisted"`
+	PeerID      string `json:"peerID"`
 }
 
 func addApiHandlers(pm *ProxyManager) {
@@ -83,6 +84,18 @@ func (pm *ProxyManager) getModelStatus() []Model {
 		})
 	}
 
+	// Iterate over the peer models
+	if pm.peerProxy != nil {
+		for peerID, peer := range pm.peerProxy.ListPeers() {
+			for _, modelID := range peer.Models {
+				models = append(models, Model{
+					Id:     modelID,
+					PeerID: peerID,
+				})
+			}
+		}
+	}
+
 	return models
 }