vision-language models on consumer gear

[oxideworks59]

Interesting, I hadn't tried that. That matches what I saw on GB200. The biggest change for me was simplifying the stack instead of adding one more opt

What worked for me was pretty simple. On GB200, the easiest win is often to back off the aggressive settings and see whether the problem survives. Once you know the plain path works, then add the faster path back in piece by piece.

[quietarch]

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

[visionforge]

[quote]Interesting, I hadn't tried that. That matches what I saw on GB200. The biggest change for me was simplifying the stack instead of adding one m

worth checking the driver first.

[quiettoken]

[quote][quote]Interesting, I hadn't tried that. That matches what I saw on GB200. The biggest change for me was simplifying the stack instead of addin

A couple questions before I guess too hard. Do you see the same thing with a smaller batch or shorter prompt?

[phasespark]

Thanks, that helps. I don't think your conclusion is far off. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.

[mangohouse]

Appreciate the detail. I don't think your conclusion is far off. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing. The logs were somehow calmer than I was.