framework overhead in real deployments

[sparrowcraft]

Thought I'd post a small recipe because a lot of threads ask similar things.

Just sharing a setup that ended up working reasonably well: Mixtral, PyTorch, mini PC, with a lot of attention on token cost.

Maybe useful as a starting point for newer folks.

[amberpatch25]

A couple things I'd check first. Before rebuilding anything, I'd test one clean baseline with FLUX and compare from there. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.

[amberrunner]

that fixed it for me too.

[visionforge]

Need a little more detail here. Are you testing this on M3 Max or something else?

[rocmrunner40]

What exact setup are you running? Is this local-only or are you routing anything externally?

I'm happy to test one more variant if you want a second data point.

[nanobrook]

I tested this tonight. My result was mixed: first run looked bad, second run looked normal. I expected the model choice to matter more than it did.

[embershed99]

A couple questions before I guess too hard. Is this local-only or are you routing anything externally?

[deepseeked]

I'd approach it in a boring order. Before rebuilding anything, I'd test one clean baseline with Gemma and compare from there.

[mangovault67]

I hit almost the same issue last night.

[kernelghost]

Not sure I agree there. I've seen people blame KV cache pressure when the real issue was much more mundane. Worth testing the simpler explanation before adopting the more interesting one.