Finish unwinding idempotent payload logic

The recent ROCm change partially removed idempotent
payloads, but the ggml-metal.metal file for mac was still
idempotent.  This finishes switching to always extract
the payloads, and now that idempotentcy is gone, the
version directory is no longer useful.

server/routes.go

@@ -1092,6 +1092,7 @@ func Serve(ln net.Listener) error {
 		if loaded.runner != nil {
 			loaded.runner.Close()
 		}
+		gpu.Cleanup()
 		os.Exit(0)
 	}()