Shared-Prefix KV Reuse Across Standard LoRA Adapters: Quality and Serving Tradeoffs
A common small-model deployment runs one shared backbone with several LoRA specialists that answer over the same context. Serving them naively re-prefills that shared context once per specialist. We study a narrow, practical question: for already-trained standard LoRA adapters -- not adapters retrained for cache compatibility -- how much task quality is preserved if the backbone's prefill KV…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
