{
  "id": 15627130,
  "title": "Improve TTFT for multi-turn agentic workloads with bi-directional KV transfer in vLLM",
  "url": "https://urgent.news/2026/10/19/improve-ttft-for-multi-turn-agentic-workloads-with-bi-directional-kv",
  "topic": "ai",
  "section": "AI",
  "published": "2026-10-19T16:03:23.000Z",
  "source": {
    "name": "AWS Machine Learning",
    "slug": "aws-machine-learning",
    "url": "https://aws.amazon.com/blogs/machine-learning/improve-ttft-for-multi-turn-agentic-workloads-with-bi-directional-kv-transfer-in-vllm/"
  },
  "original_language": "en",
  "account": null,
  "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 3.3x for GLM-5-FP8 on Amazon EC2 P5en instances with EFA.",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 2,
    "also_reported_by": [
      {
        "outlet": "AWS Machine Learning",
        "title": "Push-based KV transfer to improve TTFT and TPOT for disaggregated inference in vLLM",
        "url": "https://urgent.news/2026/10/19/push-based-kv-transfer-to-improve-ttft-and-tpot-for-disaggregated",
        "published": "2026-10-19T16:05:17.000Z"
      }
    ]
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}