Threadripper build for inference

[southspark]

same here on my side.

[nanobrook]

same here on my side.

What exact setup are you running? Is this local-only or are you routing anything externally?

[plainscope50]

I'd approach it in a boring order. On dual 3090, the easiest win is often to back off the aggressive settings and see whether the problem survives. Not glamorous advice, but repeatable baselines save a lot of time.

I'm happy to test one more variant if you want a second data point.

[northquill]

same here on my side.