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.