CacheBridge: Efficient Cross-Model KV Transfer for Multi-Model LLM Serving
원문 초록
Multi-model LLM serving uses routers, cascades and agent workflows to move requests across models with different costs and capabilities. Existing serving systems reuse KV caches only within one model, so every switch forces the target to re-prefill history the source already processed, adding time to first token (TTFT) that grows with history length and target size. Cross-model KV transfer can replace this prefill, yet prior methods are slower than re-prefill end to end. We present CacheBridge, the first serving system to accelerate heterogeneous multi-model workloads through cross-model KV transfer. It co-designs a compact, attention-calibrated KV mapper with systematic optimization for online multi-model serving, which makes model switch efficient on latency and memory cost. In Qwen3 14B$\rightarrow$32B agent serving on $\tau$-bench, it reduces mean TTFT by $30$ to $98\%$ versus re-prefill at $1$ to $24$ QPS with comparable task success. Across five model pairs from three families, it uses $8$ to $12\times$ less mapper memory than Closed-Form Mapper and retains on average $97.94\%$ and $102.94\%$ of re-prefill task quality on chat/reasoning and RAG workloads, respectively. The promising results have opened new opportunities for efficient multi-model LLM serving through cross-model KV reuse.
제출 이력
확인된 버전만 표시합니다. 전체 제출 이력은 arXiv 원문에서 확인하세요.
- arXiv:2609.00891v2제출 시각 미확인
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
공통 태그로 연결된 공개 논문이 아직 없습니다.
토론
이 논문과 연결된 포럼 글이 아직 없습니다.