+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Generative AI (https://www.datasculpting.ai/inference/forumdisplay.php?fid=17)
+--- Forum: Image (https://www.datasculpting.ai/inference/forumdisplay.php?fid=69)
+--- Thread: small speech stack for local use: anyone testing this? (/showthread.php?tid=203)
Pages:
1
2
small speech stack for local use: anyone testing this? - macropoint - 09-09-2026
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.
Re: small speech stack for local use: anyone testing this? - torchsmith25 - 09-11-2026
Quote: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.
Re: small speech stack for local use: anyone testing this? - deltastation - 09-11-2026
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.
Re: small speech stack for local use: anyone testing this? - vectorfield - 09-12-2026
that fixed it for me too.
Re: small speech stack for local use: anyone testing this? - llmtrack - 09-12-2026
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.
Re: small speech stack for local use: anyone testing this? - deltastation - 09-13-2026
Quote: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.
Re: small speech stack for local use: anyone testing this? - visionforge - 09-13-2026
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.
Re: small speech stack for local use: anyone testing this? - quiethouse - 09-14-2026
Quote: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.
Re: small speech stack for local use: anyone testing this? - visionforge - 09-14-2026
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.
Re: small speech stack for local use: anyone testing this? - southpatch - 09-14-2026
A couple questions before I guess too hard. Are you testing this on 5090 or something else?