Hello, i think there are still problems with using the GPU Server. Before the updates, there was no problem with it. It took time to time to make conversations, but now there always this problem:
[17:41:00] CtxLimit:2290/6144, Amt:194/512, Init:0.01s, Process:3.33s (23.15T/s), Generate:143.30s (1.35T/s), Total:146.62sGenerate: The response could not be sent, maybe connection was terminated?
I am using the Gemma 2 Large because is the one that describes better the role play with the NPC's than Nemo. And i was playing with it, but after the updates... is always the connection terminated even with just greet the Npcs.