small speech stack for local use: anyone testing this?

[macropoint]

Posting this in case it saves someone else a little time.

If you were starting from scratch today for this use case, what would you choose first and what would you ignore?

Would rather learn from your scars than collect my own all at once.

[torchsmith25]

Posting this in case it saves someone else a little time.

I'd approach it in a boring order. On GB200, the easiest win is often to back off the aggressive settings and see whether the problem survives.

[deltastation]

What worked for me was pretty simple. If you're on SGLang, I'd confirm the version first and then reduce variables until the behavior is obvious.

[vectorfield]

that fixed it for me too.

[llmtrack]

Interesting, I hadn't tried that. I don't think your conclusion is far off. The biggest change for me was simplifying the stack instead of adding one more optimization layer.

[deltastation]

Interesting, I hadn't tried that. I don't think your conclusion is far off. The biggest change for me was simplifying the stack instead of adding one

following this because I'm in the same boat.

[visionforge]

Thanks, that helps. The pattern around INT4 has been pretty similar for me. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.

[quiethouse]

Thanks, that helps. The pattern around INT4 has been pretty similar for me. I got better results once I stopped chasing one metric and just looked at

What worked for me was pretty simple. On B200, the easiest win is often to back off the aggressive settings and see whether the problem survives. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.

[visionforge]

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.

[southpatch]

A couple questions before I guess too hard. Are you testing this on 5090 or something else?