first LoRA that actually helped

[llm_wren]

My first guess would be this: Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at quant drift. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.

[batchsize]

Can you fill in a bit more context? What model, what runtime, and roughly what context size?

[batchsize]

worth checking the driver first.

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

[nanobrook]

Can you fill in a bit more context? What model, what runtime, and roughly what context size?

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.

[rocmriley]

that fixed it for me too.