[
  {
    "id": "cs-19-1",
    "type": "paper-conference",
    "title": "Efficient Memory Management for Large Language Model Serving with PagedAttention",
    "author": [
      {
        "given": "Woosuk",
        "family": "Kwon"
      },
      {
        "given": "Zhuohan",
        "family": "Li"
      },
      {
        "given": "Siyuan",
        "family": "Zhuang"
      },
      {
        "given": "Ying",
        "family": "Sheng"
      },
      {
        "given": "Lianmin",
        "family": "Zheng"
      },
      {
        "given": "Cody Hao",
        "family": "Yu"
      },
      {
        "given": "Joseph",
        "family": "Gonzalez"
      },
      {
        "given": "Hao",
        "family": "Zhang"
      },
      {
        "given": "Ion",
        "family": "Stoica"
      }
    ],
    "container-title": "Proceedings of the 29th Symposium on Operating Systems Principles",
    "issued": {
      "date-parts": [
        [
          2023
        ]
      ]
    },
    "DOI": "10.1145/3600006.3613165",
    "URL": "https://arxiv.org/abs/2309.06180"
  },
  {
    "id": "cs-19-2",
    "type": "paper-conference",
    "title": "FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness",
    "author": [
      {
        "given": "Tri",
        "family": "Dao"
      },
      {
        "given": "Daniel Y.",
        "family": "Fu"
      },
      {
        "given": "Stefano",
        "family": "Ermon"
      },
      {
        "given": "Atri",
        "family": "Rudra"
      },
      {
        "given": "Christopher",
        "family": "Re"
      }
    ],
    "container-title": "Advances in Neural Information Processing Systems 35",
    "issued": {
      "date-parts": [
        [
          2022
        ]
      ]
    },
    "DOI": "",
    "URL": "https://arxiv.org/abs/2205.14135"
  },
  {
    "id": "cs-19-3",
    "type": "paper-conference",
    "title": "Orca: A Distributed Serving System for Transformer-Based Generative Models",
    "author": [
      {
        "given": "Gyeong-In",
        "family": "Yu"
      },
      {
        "given": "Joo Seong",
        "family": "Jeong"
      },
      {
        "given": "Geon-Woo",
        "family": "Kim"
      },
      {
        "given": "Soojeong",
        "family": "Kim"
      },
      {
        "given": "Byung-Gon",
        "family": "Chun"
      }
    ],
    "container-title": "USENIX OSDI",
    "issued": {
      "date-parts": [
        [
          2022
        ]
      ]
    },
    "DOI": "",
    "URL": "https://www.usenix.org/conference/osdi22/presentation/yu"
  }
]
