🐦 Twitter Post Details

Viewing enriched Twitter post

@tri_dao

I really like Phil Tillet's framing of different tools having different tradeoffs in productivity and performance: torch compile, triton, CUDA, PTX. It's still early but CuTe-DSL and similar Python-based DSL might bend this curve. And soon we can probably get LLMs to generate these kernels! Phil's talk here: https://t.co/Kze5TwOzL4

Media 1

📊 Media Metadata

{
  "media": [
    {
      "type": "photo",
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/1943372635351515227/media_0.jpg?",
      "filename": "media_0.jpg"
    }
  ],
  "processed_at": "2025-12-31T22:53:15.666749",
  "pipeline_version": "2.0"
}

🔧 Raw API Response

{
  "type": "tweet",
  "id": "1943372635351515227",
  "url": "https://x.com/tri_dao/status/1943372635351515227",
  "twitterUrl": "https://twitter.com/tri_dao/status/1943372635351515227",
  "text": "I really like Phil Tillet's framing of different tools having different tradeoffs in productivity and performance: torch compile, triton, CUDA, PTX. It's still early but CuTe-DSL and similar Python-based DSL might bend this curve. And soon we can probably get LLMs to generate these kernels!\n\nPhil's talk here: https://t.co/Kze5TwOzL4",
  "source": "Twitter for iPhone",
  "retweetCount": 12,
  "replyCount": 2,
  "likeCount": 80,
  "quoteCount": 0,
  "viewCount": 6889,
  "createdAt": "Thu Jul 10 18:11:57 +0000 2025",
  "lang": "en",
  "bookmarkCount": 29,
  "isReply": true,
  "inReplyToId": "1943372100774900056",
  "conversationId": "1943372100774900056",
  "displayTextRange": [
    0,
    277
  ],
  "inReplyToUserId": null,
  "inReplyToUsername": null,
  "author": {
    "type": "user",
    "userName": "tri_dao",
    "url": "https://x.com/tri_dao",
    "twitterUrl": "https://twitter.com/tri_dao",
    "id": "568879807",
    "name": "Tri Dao",
    "isVerified": false,
    "isBlueVerified": true,
    "verifiedType": null,
    "profilePicture": "https://pbs.twimg.com/profile_images/1389486324516671496/owa9Z4AC_normal.jpg",
    "coverPicture": "",
    "description": "Asst. Prof @PrincetonCS, Chief Scientist @togethercompute. Machine learning & systems.",
    "location": "Stanford, CA",
    "followers": 35304,
    "following": 637,
    "status": "",
    "canDm": true,
    "canMediaTag": true,
    "createdAt": "Wed May 02 07:13:50 +0000 2012",
    "entities": {
      "description": {
        "urls": []
      },
      "url": {
        "urls": [
          {
            "display_url": "tridao.me",
            "expanded_url": "https://tridao.me",
            "url": "https://t.co/uFTGOmLPGP",
            "indices": [
              0,
              23
            ]
          }
        ]
      }
    },
    "fastFollowersCount": 0,
    "favouritesCount": 1582,
    "hasCustomTimelines": true,
    "isTranslator": false,
    "mediaCount": 54,
    "statusesCount": 882,
    "withheldInCountries": [],
    "affiliatesHighlightedLabel": {},
    "possiblySensitive": false,
    "pinnedTweetIds": [
      "1811453622070444071"
    ],
    "profile_bio": {
      "description": "Asst. Prof @PrincetonCS, Chief Scientist @togethercompute. Machine learning & systems."
    },
    "isAutomated": false,
    "automatedBy": null
  },
  "extendedEntities": {
    "media": [
      {
        "display_url": "pic.x.com/so8iq0QIdy",
        "expanded_url": "https://x.com/tri_dao/status/1943372635351515227/photo/1",
        "id_str": "1943372631282991104",
        "indices": [
          278,
          301
        ],
        "media_key": "3_1943372631282991104",
        "media_url_https": "https://pbs.twimg.com/media/Gvg_HJnWwAA8492.jpg",
        "type": "photo",
        "url": "https://t.co/so8iq0QIdy",
        "ext_media_availability": {
          "status": "Available"
        },
        "features": {
          "large": {
            "faces": []
          },
          "medium": {
            "faces": []
          },
          "small": {
            "faces": []
          },
          "orig": {
            "faces": []
          }
        },
        "sizes": {
          "large": {
            "h": 1033,
            "w": 1611,
            "resize": "fit"
          },
          "medium": {
            "h": 769,
            "w": 1200,
            "resize": "fit"
          },
          "small": {
            "h": 436,
            "w": 680,
            "resize": "fit"
          },
          "thumb": {
            "h": 150,
            "w": 150,
            "resize": "crop"
          }
        },
        "original_info": {
          "height": 1033,
          "width": 1611,
          "focus_rects": [
            {
              "x": 0,
              "y": 131,
              "w": 1611,
              "h": 902
            },
            {
              "x": 578,
              "y": 0,
              "w": 1033,
              "h": 1033
            },
            {
              "x": 705,
              "y": 0,
              "w": 906,
              "h": 1033
            },
            {
              "x": 1094,
              "y": 0,
              "w": 517,
              "h": 1033
            },
            {
              "x": 0,
              "y": 0,
              "w": 1611,
              "h": 1033
            }
          ]
        },
        "media_results": {
          "result": {
            "media_key": "3_1943372631282991104"
          }
        }
      }
    ]
  },
  "card": null,
  "place": {},
  "entities": {
    "hashtags": [],
    "symbols": [],
    "timestamps": [],
    "urls": [
      {
        "display_url": "semianalysis.com/wp-content/upl…",
        "expanded_url": "https://semianalysis.com/wp-content/uploads/2025/03/Blackwell-Programming-for-the-Masses-With-OpenAI-Triton-Phil-Tillet.pdf",
        "url": "https://t.co/Kze5TwOzL4",
        "indices": [
          311,
          334
        ]
      }
    ],
    "user_mentions": []
  },
  "quoted_tweet": null,
  "retweeted_tweet": null,
  "article": null
}