SOURCE-LINKED INTELLIGENCE

Shared-Prefix KV Reuse Across Standard LoRA Adapters: Quality and Serving Tradeoffs

arXiv · AI, language, vision and robotics · article · Sep 15, 2026 · UTC

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 cache is computed once and reused across specialists, and what does that buy in serving cost? On a Qwen3-1.7B backbone with two adapters (extractive QA on HotpotQA, arithmetic reasoning on GSM8K), we sweep

Read original source ↗ Open in workspace

recordType

paper

region

Global