From dd8d037c16a170dee6734f389cf285c5da319e70 Mon Sep 17 00:00:00 2001 From: Devon Rifkin Date: Sun, 27 Apr 2025 13:45:13 -0700 Subject: [PATCH] load arrays with up to 1024 elements when estimating This mirrors the old behavior before #10382 --- server/sched.go | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) 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