{"id":"3007db13-1d3c-4881-927c-fcfbc2533079","url":"https://api.tumn.com/news/3007db13-1d3c-4881-927c-fcfbc2533079","title":"Improve TTFT for multi-turn agentic workloads with bi-directional KV transfer in vLLM","summary":"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.","sections":[],"faq":[],"sources":[{"url":"https://aws.amazon.com/blogs/machine-learning/improve-ttft-for-multi-turn-agentic-workloads-with-bi-directional-kv-transfer-in-vllm/","title":"AWS Machine Learning Blog","publishedAt":"2026-10-19T16:03:23.000Z"}],"author":"TUMN 큐레이션","aiAssisted":false,"reviewStatus":"automated","reviewNote":"원문 제목과 공개된 발췌를 인용하고 원문으로 연결합니다. 내용을 재작성하거나 요약하지 않았습니다.","publishedAt":"2026-10-19T16:03:23.000Z","modifiedAt":"2026-10-19T21:25:34.000Z","checkedAt":"2026-10-19T21:25:34.322Z","language":"ko","kind":"link","sourceLabel":"AI 공식","profile":null,"via":null,"formats":{"json":"https://api.tumn.com/news/3007db13-1d3c-4881-927c-fcfbc2533079.json","markdown":"https://api.tumn.com/news/3007db13-1d3c-4881-927c-fcfbc2533079.md"}}