+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Generative AI (https://www.datasculpting.ai/inference/forumdisplay.php?fid=17)
+--- Forum: Multimodal (https://www.datasculpting.ai/inference/forumdisplay.php?fid=72)
+--- Thread: Multimodal discussion on GB200 (/showthread.php?tid=844)
Pages:
1
2
Re: Multimodal discussion on GB200 - fastlab - 10-11-2026
following this because I'm in the same boat.
Re: Multimodal discussion on GB200 - tensorriver - 10-11-2026
same here on my side.
Re: Multimodal discussion on GB200 - macrotinker - 10-11-2026
A couple questions before I guess too hard. Are you testing this on A6000 or something else?
There are a few different conversations hiding inside this thread, so being explicit about the goal helps.
Re: Multimodal discussion on GB200 - deepseeked - 10-11-2026
That matches what I was seeing. The pattern around prefix caching has been pretty similar for me.
Re: Multimodal discussion on GB200 - mintstream9 - 10-14-2026
Maybe, but I had the opposite result. I've seen people blame HBM constraints when the real issue was much more mundane. Could be a workload difference, but I wouldn't generalize too fast from one setup.
Re: Multimodal discussion on GB200 - sparrowgrid - 10-14-2026
A couple questions before I guess too hard. Do you see the same thing with a smaller batch or shorter prompt?