Threadripper build for inference

[sanevault]

Maybe, but I had the opposite result. The reported numbers can look compelling, but in ordinary usage I didn't see the same benefit. Worth testing the simpler explanation before adopting the more interesting one.

[promptfield]

My first guess would be this: Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at router policy. Not glamorous advice, but repeatable baselines save a lot of time.

[edgequill]

that fixed it for me too.

[plainscope50]

What worked for me was pretty simple. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at reranking. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.

There are a few different conversations hiding inside this thread, so being explicit about the goal helps.