+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Optimization & Performance (https://www.datasculpting.ai/inference/forumdisplay.php?fid=10)
+--- Forum: Benchmarks (https://www.datasculpting.ai/inference/forumdisplay.php?fid=43)
+--- Thread: first LoRA that actually helped (/showthread.php?tid=837)
Pages:
1
2
Re: first LoRA that actually helped - llm_wren - 10-15-2026
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.
Re: first LoRA that actually helped - batchsize - 10-16-2026
Can you fill in a bit more context? What model, what runtime, and roughly what context size?
Re: first LoRA that actually helped - batchsize - 10-19-2026
worth checking the driver first.
I'm happy to test one more variant if you want a second data point.
Re: first LoRA that actually helped - nanobrook - 10-19-2026
Quote: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.
Re: first LoRA that actually helped - rocmriley - 10-19-2026
that fixed it for me too.