Skip to content

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

server: prevent image generation models from reloading on every request (#13771)

Jeffrey Morgand51e95ba7e12
diff --git a/server/sched.go b/server/sched.go
index d83a70b36..5f22e0b87 100644
--- a/server/sched.go
+++ b/server/sched.go
@@ -571,6 +571,7 @@ func (s *Scheduler) loadImageGen(req *LlmRequest) bool {
model: req.model,
modelPath: req.model.ModelPath,
llama: server,
+ Options: &req.opts,
loading: false,
sessionDuration: sessionDuration,
totalSize: server.TotalSize(),