🐦 Twitter Post Details

Viewing enriched Twitter post

@yukangchen_

We’re thrilled to open-source TriAttention! 🚀 🦞 Deploy OpenClaw (32B LLM) on a single 24GB RTX 4090 locally 💻Full code open-source & vLLM-ready for one-click deployment ⚡️ 2.5× faster inference speed & 10.7× less KV cache memory usage TriAttention is a novel KV cache compression method built on rigorous trigonometric analysis in the Pre‑RoPE space for efficient LLM long reasoning. Github Repo: https://t.co/Gpu4E9oo3v Paper Link: https://t.co/DIWxgvlsjN Homepage: https://t.co/pDFK3mq53O

Media 2
Media 3
View on Twitter

📊 Media Metadata

{
  "media": [
    {
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2041366586423165152/media_0.mp4",
      "media_url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2041366586423165152/media_0.mp4",
      "type": "video",
      "filename": "media_0.mp4"
    },
    {
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2041366586423165152/media_1.jpg",
      "media_url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2041366586423165152/media_1.jpg",
      "type": "photo",
      "filename": "media_1.jpg"
    },
    {
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2041366586423165152/media_2.jpg",
      "media_url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2041366586423165152/media_2.jpg",
      "type": "photo",
      "filename": "media_2.jpg"
    }
  ],
  "processed_at": "2026-04-07T23:32:37.119368",
  "pipeline_version": "2.0"
}

🔧 Raw API Response

{
  "type": "tweet",
  "id": "2041366586423165152",
  "url": "https://x.com/yukangchen_/status/2041366586423165152",
  "twitterUrl": "https://twitter.com/yukangchen_/status/2041366586423165152",
  "text": "We’re thrilled to open-source TriAttention! 🚀\n\n🦞 Deploy OpenClaw (32B LLM) on a single 24GB RTX 4090 locally\n 💻Full code open-source & vLLM-ready for one-click deployment\n⚡️ 2.5× faster inference speed & 10.7× less KV cache memory usage\n\nTriAttention is a novel KV cache compression method built on rigorous trigonometric analysis in the Pre‑RoPE space for efficient LLM long reasoning.\n\nGithub Repo: https://t.co/Gpu4E9oo3v\nPaper Link: https://t.co/DIWxgvlsjN\nHomepage: https://t.co/pDFK3mq53O",
  "source": "Twitter for iPhone",
  "retweetCount": 102,
  "replyCount": 21,
  "likeCount": 766,
  "quoteCount": 19,
  "viewCount": 72979,
  "createdAt": "Tue Apr 07 04:04:55 +0000 2026",
  "lang": "en",
  "bookmarkCount": 731,
  "isReply": false,
  "inReplyToId": null,
  "conversationId": "2041366586423165152",
  "displayTextRange": [
    0,
    278
  ],
  "inReplyToUserId": null,
  "inReplyToUsername": null,
  "author": {
    "type": "user",
    "userName": "yukangchen_",
    "url": "https://x.com/yukangchen_",
    "twitterUrl": "https://twitter.com/yukangchen_",
    "id": "1871113398726901760",
    "name": "Yukang Chen",
    "isVerified": false,
    "isBlueVerified": true,
    "verifiedType": null,
    "profilePicture": "https://pbs.twimg.com/profile_images/1979021303429365760/wfEJ8_WO_normal.jpg",
    "coverPicture": "https://pbs.twimg.com/profile_banners/1871113398726901760/1734951202",
    "description": "",
    "location": "Boston USA",
    "followers": 849,
    "following": 118,
    "status": "",
    "canDm": false,
    "canMediaTag": true,
    "createdAt": "Mon Dec 23 08:40:17 +0000 2024",
    "entities": {
      "description": {
        "urls": []
      },
      "url": {}
    },
    "fastFollowersCount": 0,
    "favouritesCount": 79,
    "hasCustomTimelines": true,
    "isTranslator": false,
    "mediaCount": 20,
    "statusesCount": 59,
    "withheldInCountries": [],
    "affiliatesHighlightedLabel": {},
    "possiblySensitive": false,
    "pinnedTweetIds": [
      "2020834182042357829"
    ],
    "profile_bio": {
      "description": "Research Scientist @NVIDIA, work in Efficient and Long AI.",
      "entities": {
        "description": {
          "hashtags": [],
          "symbols": [],
          "urls": [],
          "user_mentions": [
            {
              "id_str": "0",
              "indices": [
                19,
                26
              ],
              "name": "",
              "screen_name": "NVIDIA"
            }
          ]
        },
        "url": {
          "urls": [
            {
              "display_url": "yukangchen.com",
              "expanded_url": "https://yukangchen.com",
              "indices": [
                0,
                23
              ],
              "url": "https://t.co/3XTPGxIfVP"
            }
          ]
        }
      }
    },
    "isAutomated": false,
    "automatedBy": null
  },
  "extendedEntities": {
    "media": [
      {
        "additional_media_info": {
          "monetizable": true
        },
        "allow_download_status": {
          "allow_download": true
        },
        "display_url": "pic.twitter.com/PiOGj2pp65",
        "expanded_url": "https://twitter.com/yukangchen_/status/2041366586423165152/video/1",
        "ext_media_availability": {
          "status": "Available"
        },
        "id_str": "2041366276900311040",
        "indices": [
          279,
          302
        ],
        "media_key": "13_2041366276900311040",
        "media_results": {
          "id": "QXBpTWVkaWFSZXN1bHRzOgwABAoAARxUY9AvGtAAAAA=",
          "result": {
            "__typename": "ApiMedia",
            "id": "QXBpTWVkaWE6DAAECgABHFRj0C8a0AAAAA==",
            "media_key": "13_2041366276900311040"
          }
        },
        "media_url_https": "https://pbs.twimg.com/amplify_video_thumb/2041366276900311040/img/t8li7Y6ns-pXzONW.jpg",
        "original_info": {
          "focus_rects": [],
          "height": 1080,
          "width": 1920
        },
        "sizes": {
          "large": {
            "h": 1080,
            "w": 1920
          }
        },
        "type": "video",
        "url": "https://t.co/PiOGj2pp65",
        "video_info": {
          "aspect_ratio": [
            16,
            9
          ],
          "duration_millis": 28023,
          "variants": [
            {
              "content_type": "application/x-mpegURL",
              "url": "https://video.twimg.com/amplify_video/2041366276900311040/pl/Y_hRjn7m0OdI1aYL.m3u8?tag=21&v=cfc"
            },
            {
              "bitrate": 256000,
              "content_type": "video/mp4",
              "url": "https://video.twimg.com/amplify_video/2041366276900311040/vid/avc1/480x270/nZWdKCbEoSLsl3al.mp4?tag=21"
            },
            {
              "bitrate": 832000,
              "content_type": "video/mp4",
              "url": "https://video.twimg.com/amplify_video/2041366276900311040/vid/avc1/640x360/0FfFnfaF56x4fpCd.mp4?tag=21"
            },
            {
              "bitrate": 2176000,
              "content_type": "video/mp4",
              "url": "https://video.twimg.com/amplify_video/2041366276900311040/vid/avc1/1280x720/7SYMXzdBYqwEftVH.mp4?tag=21"
            },
            {
              "bitrate": 10368000,
              "content_type": "video/mp4",
              "url": "https://video.twimg.com/amplify_video/2041366276900311040/vid/avc1/1920x1080/sqeAbV7bBoNrFqH6.mp4?tag=21"
            }
          ]
        }
      }
    ]
  },
  "card": null,
  "place": {},
  "entities": {
    "hashtags": [],
    "symbols": [],
    "timestamps": [],
    "urls": [
      {
        "display_url": "github.com/WeianMao/triat…",
        "expanded_url": "https://github.com/WeianMao/triattention",
        "indices": [
          401,
          424
        ],
        "url": "https://t.co/Gpu4E9oo3v"
      },
      {
        "display_url": "huggingface.co/papers/2604.04…",
        "expanded_url": "https://huggingface.co/papers/2604.04921",
        "indices": [
          437,
          460
        ],
        "url": "https://t.co/DIWxgvlsjN"
      },
      {
        "display_url": "weianmao.github.io/tri-attention-…",
        "expanded_url": "https://weianmao.github.io/tri-attention-project-page",
        "indices": [
          471,
          494
        ],
        "url": "https://t.co/pDFK3mq53O"
      }
    ],
    "user_mentions": []
  },
  "quoted_tweet": null,
  "retweeted_tweet": null,
  "isLimitedReply": false,
  "communityInfo": null,
  "article": null
}