@tri_dao
Attack of the asynchronous machines. We’ve seen this a lot in GPU kernels. This time the same principle applies in speculative decoding
🐦 Twitter Post Details
Viewing enriched Twitter post
📊 Media Metadata
{
"score": 0.32,
"score_components": {
"author": 0.09,
"engagement": 0.0,
"quality": 0.020000000000000004,
"source": 0.135,
"nlp": 0.05,
"recency": 0.025
},
"scored_at": "2026-03-06T07:22:22.922196",
"import_source": "api_import",
"source_tagged_at": "2026-03-06T07:22:22.922203",
"enriched": true,
"enriched_at": "2026-03-06T07:22:22.922205"
}🔧 Raw API Response
{
"type": "tweet",
"id": "2029273056364118407",
"url": "https://x.com/tri_dao/status/2029273056364118407",
"twitterUrl": "https://twitter.com/tri_dao/status/2029273056364118407",
"text": "Attack of the asynchronous machines. We’ve seen this a lot in GPU kernels. This time the same principle applies in speculative decoding",
"source": "Twitter for iPhone",
"retweetCount": 29,
"replyCount": 6,
"likeCount": 521,
"quoteCount": 2,
"viewCount": 39090,
"createdAt": "Wed Mar 04 19:09:33 +0000 2026",
"lang": "en",
"bookmarkCount": 190,
"isReply": false,
"inReplyToId": null,
"conversationId": "2029273056364118407",
"displayTextRange": [
0,
135
],
"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": "",
"location": "Stanford, CA",
"followers": 37865,
"following": 643,
"status": "",
"canDm": true,
"canMediaTag": true,
"createdAt": "Wed May 02 07:13:50 +0000 2012",
"entities": {
"description": {
"urls": []
},
"url": {}
},
"fastFollowersCount": 0,
"favouritesCount": 1610,
"hasCustomTimelines": true,
"isTranslator": false,
"mediaCount": 54,
"statusesCount": 901,
"withheldInCountries": [],
"affiliatesHighlightedLabel": {},
"possiblySensitive": false,
"pinnedTweetIds": [
"1811453622070444071"
],
"profile_bio": {
"description": "Asst. Prof @PrincetonCS, Chief Scientist @togethercompute. Machine learning & systems.",
"entities": {
"description": {
"hashtags": [],
"symbols": [],
"urls": [],
"user_mentions": [
{
"id_str": "0",
"indices": [
11,
23
],
"name": "",
"screen_name": "PrincetonCS"
},
{
"id_str": "0",
"indices": [
41,
57
],
"name": "",
"screen_name": "togethercompute"
}
]
},
"url": {
"urls": [
{
"display_url": "tridao.me",
"expanded_url": "https://tridao.me",
"indices": [
0,
23
],
"url": "https://t.co/uFTGOmLPGP"
}
]
}
}
},
"isAutomated": false,
"automatedBy": null
},
"extendedEntities": {},
"card": null,
"place": {},
"entities": {
"hashtags": [],
"symbols": [],
"timestamps": [],
"urls": [],
"user_mentions": []
},
"quoted_tweet": {
"type": "tweet",
"id": "2029251146196631872",
"url": "https://x.com/tanishqkumar07/status/2029251146196631872",
"twitterUrl": "https://twitter.com/tanishqkumar07/status/2029251146196631872",
"text": "I've been working on a new LLM inference algorithm. \n\nIt's called Speculative Speculative Decoding (SSD) and it's up to 2x faster than the strongest inference engines in the world. \n\nCollab w/ @tri_dao @avnermay. Details in thread.",
"source": "Twitter for iPhone",
"retweetCount": 439,
"replyCount": 127,
"likeCount": 3953,
"quoteCount": 97,
"viewCount": 570015,
"createdAt": "Wed Mar 04 17:42:29 +0000 2026",
"lang": "en",
"bookmarkCount": 2700,
"isReply": false,
"inReplyToId": null,
"conversationId": "2029251146196631872",
"displayTextRange": [
0,
232
],
"inReplyToUserId": null,
"inReplyToUsername": null,
"author": {
"type": "user",
"userName": "tanishqkumar07",
"url": "https://x.com/tanishqkumar07",
"twitterUrl": "https://twitter.com/tanishqkumar07",
"id": "1544735653828624384",
"name": "Tanishq Kumar",
"isVerified": false,
"isBlueVerified": true,
"verifiedType": null,
"profilePicture": "https://pbs.twimg.com/profile_images/1904982101314998272/Wnplx6-n_normal.jpg",
"coverPicture": "https://pbs.twimg.com/profile_banners/1544735653828624384/1739719120",
"description": "",
"location": "Stanford, CA",
"followers": 5048,
"following": 79,
"status": "",
"canDm": true,
"canMediaTag": true,
"createdAt": "Wed Jul 06 17:31:04 +0000 2022",
"entities": {
"description": {
"urls": []
},
"url": {}
},
"fastFollowersCount": 0,
"favouritesCount": 393,
"hasCustomTimelines": true,
"isTranslator": false,
"mediaCount": 15,
"statusesCount": 133,
"withheldInCountries": [],
"affiliatesHighlightedLabel": {},
"possiblySensitive": false,
"pinnedTweetIds": [
"2029251146196631872"
],
"profile_bio": {
"description": "CS PhD student @StanfordAILab. prev math undergrad @Harvard",
"entities": {
"description": {
"hashtags": [],
"symbols": [],
"urls": [],
"user_mentions": [
{
"id_str": "0",
"indices": [
15,
29
],
"name": "",
"screen_name": "StanfordAILab"
},
{
"id_str": "0",
"indices": [
51,
59
],
"name": "",
"screen_name": "Harvard"
}
]
},
"url": {
"urls": [
{
"display_url": "tanishqkumar.github.io",
"expanded_url": "http://tanishqkumar.github.io",
"indices": [
0,
23
],
"url": "https://t.co/LD18pD2k9Y"
}
]
}
}
},
"isAutomated": false,
"automatedBy": null
},
"extendedEntities": {
"media": [
{
"additional_media_info": {
"monetizable": false
},
"allow_download_status": {
"allow_download": true
},
"display_url": "pic.twitter.com/fbjwL7RWcy",
"expanded_url": "https://twitter.com/tanishqkumar07/status/2029251146196631872/video/1",
"ext_media_availability": {
"status": "Available"
},
"id_str": "2029251097685319680",
"indices": [
233,
256
],
"media_key": "13_2029251097685319680",
"media_results": {
"id": "QXBpTWVkaWFSZXN1bHRzOgwABAoAARwpWR81muAAAAA=",
"result": {
"__typename": "ApiMedia",
"id": "QXBpTWVkaWE6DAAECgABHClZHzWa4AAAAA==",
"media_key": "13_2029251097685319680"
}
},
"media_url_https": "https://pbs.twimg.com/amplify_video_thumb/2029251097685319680/img/4o82UnXLxQc_4OIp.jpg",
"original_info": {
"focus_rects": [],
"height": 720,
"width": 1278
},
"sizes": {
"large": {
"h": 720,
"w": 1278
}
},
"type": "video",
"url": "https://t.co/fbjwL7RWcy",
"video_info": {
"aspect_ratio": [
71,
40
],
"duration_millis": 9066,
"variants": [
{
"content_type": "application/x-mpegURL",
"url": "https://video.twimg.com/amplify_video/2029251097685319680/pl/CsxHlQe-pWojYALC.m3u8?tag=21"
},
{
"bitrate": 256000,
"content_type": "video/mp4",
"url": "https://video.twimg.com/amplify_video/2029251097685319680/vid/avc1/478x270/Ty-p2MBx3ihidfBD.mp4?tag=21"
},
{
"bitrate": 832000,
"content_type": "video/mp4",
"url": "https://video.twimg.com/amplify_video/2029251097685319680/vid/avc1/638x360/Yd9SVczQrpGr90jd.mp4?tag=21"
},
{
"bitrate": 2176000,
"content_type": "video/mp4",
"url": "https://video.twimg.com/amplify_video/2029251097685319680/vid/avc1/1278x720/OURIy6CwE_UF4J5u.mp4?tag=21"
}
]
}
}
]
},
"card": null,
"place": {},
"entities": {
"hashtags": [],
"symbols": [],
"timestamps": [],
"urls": [],
"user_mentions": [
{
"id_str": "568879807",
"indices": [
194,
202
],
"name": "Tri Dao",
"screen_name": "tri_dao"
},
{
"id_str": "41314685",
"indices": [
203,
212
],
"name": "Avner May",
"screen_name": "avnermay"
}
]
},
"quoted_tweet": null,
"retweeted_tweet": null,
"isLimitedReply": false,
"article": null
},
"retweeted_tweet": null,
"isLimitedReply": false,
"article": null
}