ml/backend/ggml: consolidate system info logging

- output backend system info when initializing the backend. this ensures
  this information is always present without needing to be called
  explicitly
- convert to structured logging
- enumerate devices rather than backends since devices are ordered
- track device indices grouped by device name

runner/llamarunner/runner.go

@@ -931,7 +931,6 @@ func Execute(args []string) error {
 	slog.Info("starting go runner")
 
 	llama.BackendInit()
-	slog.Info("system", "info", llama.PrintSystemInfo(), "threads", *threads)
 
 	server := &Server{
 		batchSize: *batchSize,

runner/ollamarunner/runner.go

@@ -786,8 +786,6 @@ func (s *Server) loadModel(
 		panic(err)
 	}
 
-	slog.Info("system", "info", s.model.Backend().SystemInfo(), "threads", params.NumThreads)
-
 	// TODO(jessegross): LoRA loading
 	if lpath.String() != "" {
 		panic("loras are not yet implemented")