Skip to content

Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

llamarunner: Init GGML before printing system info

Jesse Gross010313bb63e7
diff --git a/runner/llamarunner/runner.go b/runner/llamarunner/runner.go
index 93d6bfabe..72873ec4d 100644
--- a/runner/llamarunner/runner.go
+++ b/runner/llamarunner/runner.go
@@ -845,8 +845,6 @@ func (s *Server) loadModel(
threads int,
multiUserCache bool,
) {
- llama.BackendInit()
-
var err error
s.model, err = llama.LoadModelFromFile(mpath, params)
if err != nil {
@@ -932,6 +930,8 @@ func Execute(args []string) error {
})
slog.SetDefault(slog.New(handler))
slog.Info("starting go runner")
+
+ llama.BackendInit()
slog.Info("system", "info", llama.PrintSystemInfo(), "threads", *threads)
server := &Server{