diff --git a/server/sched.go b/server/sched.go index 612e47020..e71cdd1bd 100644 --- a/server/sched.go +++ b/server/sched.go @@ -191,7 +191,7 @@ func (s *Scheduler) processPending(ctx context.Context) { } // Load model for fitting - ggml, err := llm.LoadModel(pending.model.ModelPath, 0) + ggml, err := llm.LoadModel(pending.model.ModelPath, 1024) if err != nil { pending.errCh <- err break