🐦 Twitter Post Details

Viewing enriched Twitter post

@askalphaxiv

“Sparser, Faster, Lighter Transformer Language Models” LLMs are naturally sparse in their feedforward layers, but unstructured sparsity usually doesn’t get you real speed on GPUs, because the hardware stack is built for dense compute. The key idea of the paper is to redesign the sparse format and kernels around GPU execution, so FFN sparsity becomes practical instead of theoretical. With mild L1 regularization, this paper got >99% sparsity with little quality loss, and with gains in speed, memory, and energy.

Media 1
View on Twitter

📊 Media Metadata

{
  "media": [
    {
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2053199273437569327/media_0.jpg",
      "media_url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2053199273437569327/media_0.jpg",
      "type": "photo",
      "filename": "media_0.jpg"
    }
  ],
  "processed_at": "2026-05-11T22:58:34.973649",
  "pipeline_version": "2.0"
}

🔧 Raw API Response

{
  "type": "tweet",
  "id": "2053199273437569327",
  "url": "https://x.com/askalphaxiv/status/2053199273437569327",
  "twitterUrl": "https://twitter.com/askalphaxiv/status/2053199273437569327",
  "text": "“Sparser, Faster, Lighter Transformer Language Models”\n\nLLMs are naturally sparse in their feedforward layers, but unstructured sparsity usually doesn’t get you real speed on GPUs, because the hardware stack is built for dense compute.\n\nThe key idea of the paper is to redesign the sparse format and kernels around GPU execution, so FFN sparsity becomes practical instead of theoretical.\n\nWith mild L1 regularization, this paper got >99% sparsity with little quality loss, and with gains in speed, memory, and energy.",
  "source": "Twitter for iPhone",
  "retweetCount": 54,
  "replyCount": 5,
  "likeCount": 406,
  "quoteCount": 5,
  "viewCount": 22640,
  "createdAt": "Sat May 09 19:43:48 +0000 2026",
  "lang": "en",
  "bookmarkCount": 245,
  "isReply": false,
  "inReplyToId": null,
  "conversationId": "2053199273437569327",
  "displayTextRange": [
    0,
    277
  ],
  "inReplyToUserId": null,
  "inReplyToUsername": null,
  "author": {
    "type": "user",
    "userName": "askalphaxiv",
    "url": "https://x.com/askalphaxiv",
    "twitterUrl": "https://twitter.com/askalphaxiv",
    "id": "1722422481942884352",
    "name": "alphaXiv",
    "isVerified": false,
    "isBlueVerified": true,
    "verifiedType": null,
    "profilePicture": "https://pbs.twimg.com/profile_images/1866663567417806848/-Vj32Dq-_normal.jpg",
    "coverPicture": "https://pbs.twimg.com/profile_banners/1722422481942884352/1738960325",
    "description": "",
    "location": "",
    "followers": 42185,
    "following": 48,
    "status": "",
    "canDm": true,
    "canMediaTag": true,
    "createdAt": "Thu Nov 09 01:15:23 +0000 2023",
    "entities": {
      "description": {
        "urls": []
      },
      "url": {}
    },
    "fastFollowersCount": 0,
    "favouritesCount": 3505,
    "hasCustomTimelines": true,
    "isTranslator": false,
    "mediaCount": 948,
    "statusesCount": 2071,
    "withheldInCountries": [],
    "affiliatesHighlightedLabel": {},
    "possiblySensitive": false,
    "pinnedTweetIds": [
      "2034003206217601375"
    ],
    "profile_bio": {
      "description": "High fidelity research",
      "entities": {
        "description": {},
        "url": {
          "urls": [
            {
              "display_url": "alphaxiv.org",
              "expanded_url": "http://alphaxiv.org",
              "indices": [
                0,
                23
              ],
              "url": "https://t.co/7lQNcnzeZ7"
            }
          ]
        }
      }
    },
    "isAutomated": false,
    "automatedBy": null
  },
  "extendedEntities": {
    "media": [
      {
        "allow_download_status": {
          "allow_download": true
        },
        "display_url": "pic.twitter.com/GHkMwQGrLe",
        "expanded_url": "https://twitter.com/askalphaxiv/status/2053199273437569327/photo/1",
        "ext_media_availability": {
          "status": "Available"
        },
        "features": {
          "large": {
            "faces": []
          },
          "orig": {
            "faces": []
          }
        },
        "id_str": "2053199207473815552",
        "indices": [
          278,
          301
        ],
        "media_key": "3_2053199207473815552",
        "media_results": {
          "id": "QXBpTWVkaWFSZXN1bHRzOgwAAQoAARx+bc0GlyAACgACHH5t3GJWIS8AAA==",
          "result": {
            "__typename": "ApiMedia",
            "id": "QXBpTWVkaWE6DAABCgABHH5tzQaXIAAKAAIcfm3cYlYhLwAA",
            "media_key": "3_2053199207473815552"
          }
        },
        "media_url_https": "https://pbs.twimg.com/media/HH5tzQaXIAA5-7m.jpg",
        "original_info": {
          "focus_rects": [
            {
              "h": 745,
              "w": 1330,
              "x": 0,
              "y": 0
            },
            {
              "h": 1330,
              "w": 1330,
              "x": 0,
              "y": 0
            },
            {
              "h": 1516,
              "w": 1330,
              "x": 0,
              "y": 0
            },
            {
              "h": 1810,
              "w": 905,
              "x": 0,
              "y": 0
            },
            {
              "h": 1810,
              "w": 1330,
              "x": 0,
              "y": 0
            }
          ],
          "height": 1810,
          "width": 1330
        },
        "sizes": {
          "large": {
            "h": 1810,
            "w": 1330
          }
        },
        "type": "photo",
        "url": "https://t.co/GHkMwQGrLe"
      }
    ]
  },
  "card": null,
  "place": {},
  "entities": {
    "hashtags": [],
    "symbols": [],
    "urls": [],
    "user_mentions": []
  },
  "quoted_tweet": null,
  "retweeted_tweet": null,
  "isLimitedReply": false,
  "communityInfo": null,
  "article": null
}