Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
load arrays with up to 1024 elements when estimating
Devon Rifkind2ee599dcf97
diff --git a/server/sched.go b/server/sched.goindex d5b19fbfd..9c13f6cf5 100644--- a/server/sched.go+++ b/server/sched.go@@ -201,7 +201,7 @@ 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 <- errbreak