{
  "type": "tweet",
  "id": "2067641904049885492",
  "url": "https://x.com/vllm_project/status/2067641904049885492",
  "twitterUrl": "https://twitter.com/vllm_project/status/2067641904049885492",
  "text": "Huge milestone from the @anyscalecompute  + @googlecloud  GKE teams 🎊\n\nRay Serve LLM provides up to 4.4x higher throughput on prefill-heavy workloads and 24x on decode-heavy workloads than previous versions.\n\nThree optimizations made this possible on the Ray Serve LLM + vLLM stack:\n⭐️Direct streaming with a control-plane-only endpoint picker\n⭐️ A new vLLM Ray V2 executor backend\n⭐️HAProxy ingress for routing at the speed of C\n\nRay's primitives for fault tolerance, observability, and portability across K8s and VMs are a great foundation as inference deployments get more complex.\n\nCongrats to the team! Try the new Ray V2 executor today in vLLM with --distributed-executor-backend ray.",
  "source": "Twitter for iPhone",
  "retweetCount": 25,
  "replyCount": 4,
  "likeCount": 109,
  "quoteCount": 0,
  "viewCount": 18207,
  "createdAt": "Thu Jun 18 16:13:39 +0000 2026",
  "lang": "en",
  "bookmarkCount": 37,
  "isReply": false,
  "inReplyToId": null,
  "conversationId": "2067641904049885492",
  "displayTextRange": [
    0,
    275
  ],
  "inReplyToUserId": null,
  "inReplyToUsername": null,
  "author": {
    "type": "user",
    "userName": "vllm_project",
    "url": "https://x.com/vllm_project",
    "twitterUrl": "https://twitter.com/vllm_project",
    "id": "1774187564276289536",
    "name": "vLLM",
    "isVerified": false,
    "isBlueVerified": true,
    "verifiedType": null,
    "profilePicture": "https://pbs.twimg.com/profile_images/1774187681746182144/N_5NJ8B1_normal.jpg",
    "coverPicture": "https://pbs.twimg.com/profile_banners/1774187564276289536/1782328808",
    "description": "",
    "location": "",
    "followers": 42509,
    "following": 36,
    "status": "",
    "canDm": true,
    "canMediaTag": true,
    "createdAt": "Sat Mar 30 21:31:01 +0000 2024",
    "entities": {
      "description": {
        "urls": []
      },
      "url": {}
    },
    "fastFollowersCount": 0,
    "favouritesCount": 604,
    "hasCustomTimelines": true,
    "isTranslator": false,
    "mediaCount": 302,
    "statusesCount": 1072,
    "withheldInCountries": [],
    "affiliatesHighlightedLabel": {},
    "possiblySensitive": false,
    "pinnedTweetIds": [],
    "profile_bio": {
      "description": "A high-throughput and memory-efficient inference and serving engine for LLMs. Join https://t.co/lxJ0SfX5pJ to discuss together with the community!",
      "entities": {
        "description": {
          "urls": [
            {
              "display_url": "slack.vllm.ai",
              "expanded_url": "http://slack.vllm.ai",
              "indices": [
                83,
                106
              ],
              "url": "https://t.co/lxJ0SfX5pJ"
            }
          ]
        },
        "url": {
          "urls": [
            {
              "display_url": "vllm.ai",
              "expanded_url": "https://vllm.ai",
              "indices": [
                0,
                23
              ],
              "url": "https://t.co/OSHR5C6pCV"
            }
          ]
        }
      }
    },
    "isAutomated": false,
    "automatedBy": null
  },
  "extendedEntities": {},
  "card": null,
  "place": {},
  "entities": {
    "hashtags": [],
    "symbols": [],
    "urls": [],
    "user_mentions": [
      {
        "id_str": "1173110913517281280",
        "indices": [
          24,
          40
        ],
        "name": "Anyscale",
        "screen_name": "anyscalecompute"
      },
      {
        "id_str": "19367815",
        "indices": [
          44,
          56
        ],
        "name": "Google Cloud",
        "screen_name": "googlecloud"
      }
    ]
  },
  "quoted_tweet": {
    "type": "tweet",
    "id": "2067638548556316960",
    "url": "https://x.com/seiji_________/status/2067638548556316960",
    "twitterUrl": "https://twitter.com/seiji_________/status/2067638548556316960",
    "text": "Today we are excited to announce, in partnership with the GKE team at Google Cloud (@googlecloud), a major milestone in Ray Serve LLM’s production serving capability. Ray Serve LLM now matches high performance, rust-based routing frameworks such as vllm-router (@vllm_project) in benchmarks across a variety of workloads and deployment patterns.\n\nIn Ray 2.56, we see up to 4x higher request throughput on prefill-heavy workloads, and 24x higher request throughput on decode-heavy workloads 🎉",
    "source": "Twitter for iPhone",
    "retweetCount": 6,
    "replyCount": 1,
    "likeCount": 52,
    "quoteCount": 9,
    "viewCount": 31646,
    "createdAt": "Thu Jun 18 16:00:19 +0000 2026",
    "lang": "en",
    "bookmarkCount": 21,
    "isReply": false,
    "inReplyToId": null,
    "conversationId": "2067638548556316960",
    "displayTextRange": [
      0,
      279
    ],
    "inReplyToUserId": null,
    "inReplyToUsername": null,
    "author": {
      "type": "user",
      "userName": "seiji_________",
      "url": "https://x.com/seiji_________",
      "twitterUrl": "https://twitter.com/seiji_________",
      "id": "1938312144824766469",
      "name": "Seiji Eicher",
      "isVerified": false,
      "isBlueVerified": true,
      "verifiedType": null,
      "profilePicture": "https://pbs.twimg.com/profile_images/1943391316185907200/37dUAWlf_normal.jpg",
      "coverPicture": "https://pbs.twimg.com/profile_banners/1938312144824766469/1760223570",
      "description": "",
      "location": "San Francisco, CA",
      "followers": 363,
      "following": 433,
      "status": "",
      "canDm": false,
      "canMediaTag": true,
      "createdAt": "Thu Jun 26 19:03:30 +0000 2025",
      "entities": {
        "description": {
          "urls": []
        },
        "url": {}
      },
      "fastFollowersCount": 0,
      "favouritesCount": 1863,
      "hasCustomTimelines": true,
      "isTranslator": false,
      "mediaCount": 45,
      "statusesCount": 264,
      "withheldInCountries": [],
      "affiliatesHighlightedLabel": {},
      "possiblySensitive": false,
      "pinnedTweetIds": [
        "2067638548556316960"
      ],
      "profile_bio": {
        "description": "Ray + vLLM = 💘 @ Anyscale | Prev: @Stanford, @Apple",
        "entities": {
          "description": {
            "user_mentions": [
              {
                "id_str": "",
                "indices": [
                  34,
                  43
                ],
                "name": "",
                "screen_name": "Stanford"
              },
              {
                "id_str": "",
                "indices": [
                  45,
                  51
                ],
                "name": "",
                "screen_name": "Apple"
              }
            ]
          },
          "url": {
            "urls": [
              {
                "display_url": "eicher.sh",
                "expanded_url": "http://eicher.sh",
                "indices": [
                  0,
                  23
                ],
                "url": "https://t.co/ZmUcTlfhzj"
              }
            ]
          }
        }
      },
      "isAutomated": false,
      "automatedBy": null
    },
    "extendedEntities": {
      "media": [
        {
          "allow_download_status": {
            "allow_download": true
          },
          "display_url": "pic.twitter.com/aaPtR5Iuki",
          "expanded_url": "https://twitter.com/seiji_________/status/2067638548556316960/photo/1",
          "ext_master_playlist_only": [],
          "ext_media_availability": {
            "status": "Available"
          },
          "ext_playlists": [],
          "features": {
            "large": {
              "faces": []
            },
            "orig": {
              "faces": []
            }
          },
          "id_str": "2067636405745127424",
          "indices": [
            280,
            303
          ],
          "media_key": "3_2067636405745127424",
          "media_results": {
            "id": "QXBpTWVkaWFSZXN1bHRzOgwAAQoAARyxuFsxGpAACgACHLG6ThqagSAAAA==",
            "result": {
              "__typename": "ApiMedia",
              "id": "QXBpTWVkaWE6DAABCgABHLG4WzEakAAKAAIcsbpOGpqBIAAA",
              "media_key": "3_2067636405745127424"
            }
          },
          "media_url_https": "https://pbs.twimg.com/media/HLG4WzEakAAHj8g.jpg",
          "original_info": {
            "focus_rects": [
              {
                "h": 1304,
                "w": 2329,
                "x": 0,
                "y": 0
              },
              {
                "h": 1483,
                "w": 1483,
                "x": 846,
                "y": 0
              },
              {
                "h": 1483,
                "w": 1301,
                "x": 1028,
                "y": 0
              },
              {
                "h": 1483,
                "w": 742,
                "x": 1315,
                "y": 0
              },
              {
                "h": 1483,
                "w": 2329,
                "x": 0,
                "y": 0
              }
            ],
            "height": 1483,
            "width": 2329
          },
          "sizes": {
            "large": {
              "h": 1304,
              "w": 2048
            }
          },
          "type": "photo",
          "url": "https://t.co/aaPtR5Iuki"
        }
      ]
    },
    "card": null,
    "place": {},
    "entities": {
      "hashtags": [],
      "symbols": [],
      "urls": [],
      "user_mentions": [
        {
          "id_str": "19367815",
          "indices": [
            84,
            96
          ],
          "name": "Google Cloud",
          "screen_name": "googlecloud"
        },
        {
          "id_str": "1774187564276289536",
          "indices": [
            262,
            275
          ],
          "name": "vLLM",
          "screen_name": "vllm_project"
        }
      ]
    },
    "quoted_tweet": null,
    "retweeted_tweet": null,
    "isLimitedReply": false,
    "communityInfo": null,
    "article": null
  },
  "retweeted_tweet": null,
  "isLimitedReply": false,
  "communityInfo": null,
  "article": null
}