+- 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 (/showthread.php?tid=664)
Pages:
1
2
Multimodal discussion - macropilot - 10-03-2026
Spent some time on this today and wanted to compare notes.
I've gone back and forth between PyTorch and Ollama for Qwen. The interesting difference for me has been batch size.
What would you pick if you had to live with it for a few months?
Re: Multimodal discussion - signalcraft14 - 10-04-2026
I'd approach it in a boring order. If you're on llama.cpp, I'd confirm the version first and then reduce variables until the behavior is obvious. Not glamorous advice, but repeatable baselines save a lot of time.
Re: Multimodal discussion - visionforge - 10-05-2026
I think the bottleneck is somewhere else. I wouldn't optimize around that first. On my side the bigger swing came from the runtime and not the model. Could be a workload difference, but I wouldn't generalize too fast from one setup.
Re: Multimodal discussion - southtinker - 10-05-2026
I'd approach it in a boring order. On 5090, the easiest win is often to back off the aggressive settings and see whether the problem survives. Not glamorous advice, but repeatable baselines save a lot of time.
Re: Multimodal discussion - vramscope - 10-05-2026
Need a little more detail here. Do you see the same thing with a smaller batch or shorter prompt?
Re: Multimodal discussion - mintquill - 10-06-2026
I'd approach it in a boring order. If you're on LM Studio, I'd confirm the version first and then reduce variables until the behavior is obvious. Not glamorous advice, but repeatable baselines save a lot of time.
Re: Multimodal discussion - batchwire - 10-06-2026
A couple things I'd check first. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at continuous batching.
Re: Multimodal discussion - localtinker - 10-06-2026
Ran a quick check on my box. I couldn't reproduce the slowdown until I pushed context much higher. The surprise was that memory pressure showed up before throughput collapsed.
Re: Multimodal discussion - mintstream9 - 10-09-2026
Quote:Ran a quick check on my box. I couldn't reproduce the slowdown until I pushed context much higher. The surprise was that memory pressure showed up bef
My first guess would be this: If you're on PyTorch, I'd confirm the version first and then reduce variables until the behavior is obvious. Not glamorous advice, but repeatable baselines save a lot of time.
Re: Multimodal discussion - lablab - 10-10-2026
Quote:[quote]Ran a quick check on my box. I couldn't reproduce the slowdown until I pushed context much higher. The surprise was that memory pressure showed
Tried to reproduce it just now. My result was mixed: first run looked bad, second run looked normal. The surprise was that memory pressure showed up before throughput collapsed.