2601.12904v1.pdf

{
  "file/base": {
    "record": {
      "extension": ".pdf",
      "hash": "e165836960d804b3db6dca7ccccaadd5ff0592749db845d95107a63630265514",
      "media_type": "application/pdf",
      "media_type_prefix": "application",
      "name": "2601.12904v1.pdf",
      "size": 2688568
    },
    "source": {
      "execution_id": "177d4346-2471-4b35-af7d-539c20e4d384",
      "id": "file/base",
      "type": "Model",
      "version": "1.0.0"
    }
  },
  "file/pdf": {
    "private": false,
    "record": {
      "creation_date": "2026-01-21T02:43:11Z",
      "keywords": [
        "Large Language Models",
        "Retrieval-Augmented Generation",
        "KVCache",
        "Prefix Caching",
        "Inference Acceleration",
        "Cache Management"
      ],
      "modified_date": "2026-01-21T02:43:11Z",
      "page_count": 28,
      "producer": "pikepdf 8.15.1",
      "subject": "-  Computing methodologies  -\u003e  Natural language processing.",
      "title": "From Prefix Cache to Fusion RAG Cache: Accelerating LLM Inference in Retrieval-Augmented Generation",
      "version": "1.7"
    },
    "source": {
      "execution_id": "5fbb4781-44e1-4778-94d9-12116bbda434",
      "id": "dorsal/pdf",
      "type": "Model",
      "version": "1.1.0"
    }
  }
}