Multimodal discussion

[macropilot]

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?

[signalcraft14]

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.

[visionforge]

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.

[southtinker]

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.

[vramscope]

Need a little more detail here. Do you see the same thing with a smaller batch or shorter prompt?

[mintquill]

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.

[batchwire]

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.

[localtinker]

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.

[mintstream9]

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.

[lablab]

[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.