# Improve TTFT for multi-turn agentic workloads with bi-directional KV transfer in vLLM

Multi-turn agentic workloads reprocess growing conversation context each turn, driving up latency. See how bi-directional KV cache transfer lets prefill and decode nodes reuse previously computed context across turns, cutting time to first token by up to 1.6x for Qwen3-32B and 3.



## 질문과 답변



## 출처
- AWS Machine Learning Blog: https://aws.amazon.com/blogs/machine-learning/improve-ttft-for-multi-turn-agentic-workloads-with-bi-directional-kv-transfer-in-vllm/ (발표 2026-10-19T16:03:23.000Z)

작성: TUMN 큐레이션 · AI 보조: false
발행: 2026-10-19T16:03:23.000Z
확인: 2026-10-19T21:25:34.322Z
검토: 원문 제목과 공개된 발췌를 인용하고 원문으로 연결합니다. 내용을 재작성하거나 요약하지 않았습니다.
정식 URL: https://api.tumn.com/news/3007db13-1d3c-4881-927c-fcfbc2533079