+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Miscellaneous Discussion (https://www.datasculpting.ai/inference/forumdisplay.php?fid=24)
+--- Forum: News & Industry (https://www.datasculpting.ai/inference/forumdisplay.php?fid=26)
+--- Thread: industry move that matters for local users (/showthread.php?tid=146)
Pages:
1
2
industry move that matters for local users - audiopoint18 - 09-06-2026
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?
Simple and boring is a valid answer.
Re: industry move that matters for local users - audiopath66 - 09-07-2026
I think the bottleneck is somewhere else. I get why that seems right, but on GB200 the bottleneck felt elsewhere. Worth testing the simpler explanation before adopting the more interesting one. The logs were somehow calmer than I was.
Re: industry move that matters for local users - phaseshed - 09-07-2026
Quote:I think the bottleneck is somewhere else. I get why that seems right, but on GB200 the bottleneck felt elsewhere. Worth testing the simpler explanatio
That matches what I was seeing. I don't think your conclusion is far off.
Re: industry move that matters for local users - audiopoint18 - 09-10-2026
Did a small comparison this afternoon. My result was mixed: first run looked bad, second run looked normal. The main thing that moved was latency, not quality.
Re: industry move that matters for local users - bytestack - 09-11-2026
that fixed it for me too.
Re: industry move that matters for local users - dockbrook21 - 09-11-2026
Maybe, but I had the opposite result. I get why that seems right, but on GB200 the bottleneck felt elsewhere. Not saying you're wrong, just that I wouldn't lock that in as the lesson yet.
Re: industry move that matters for local users - audiopoint18 - 09-11-2026
Tried to reproduce it just now. I couldn't reproduce the slowdown until I pushed context much higher. The main thing that moved was latency, not quality.
Re: industry move that matters for local users - southpatch - 09-13-2026
A couple things I'd check first. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at HBM constraints. Once you know the plain path works, then add the faster path back in piece by piece.
Re: industry move that matters for local users - edgecoast - 09-13-2026
My first guess would be this: Before rebuilding anything, I'd test one clean baseline with Mistral and compare from there. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
Re: industry move that matters for local users - dockriver - 09-16-2026
same here on my side.