little utility you keep installed: worth it?

[mlxgarden]

I'm trying to sanity-check my setup.

I'm trying to decide whether to keep the current stack or change course. Main question is how people here are handling long context.

Would appreciate practical advice rather than theory.

[deltagrid]

A couple things I'd check first. Before rebuilding anything, I'd test one clean baseline with Kimi and compare from there. Once you know the plain path works, then add the faster path back in piece by piece.

[audioriver]

same here on my side.

[deepseeked]

same here on my side.

A couple things I'd check first. If you're on SGLang, I'd confirm the version first and then reduce variables until the behavior is obvious.

[batchyard]

Thanks, that helps. That matches what I saw on dual 3090. The biggest change for me was simplifying the stack instead of adding one more optimization layer.

[relayforge]

I think the bottleneck is somewhere else. The reported numbers can look compelling, but in ordinary usage I didn't see the same benefit.

[rocmriley]

Not sure I agree there. I've seen people blame NVFP4 when the real issue was much more mundane. Worth testing the simpler explanation before adopting the more interesting one.

[mangoquill]

A couple questions before I guess too hard. Are you testing this on B200 or something else?

[rocmhouse90]

A couple things I'd check first. Before rebuilding anything, I'd test one clean baseline with Mixtral and compare from there. Not glamorous advice, but repeatable baselines save a lot of time.

[batchshed]

same here on my side.