@drisspg
I alluded to this a few tweets ago but just pushed up a shortish blog on a subtle feature of CLC work stealing that makes cuda-graphable grouped_gemm possible with this scheduling mode: https://t.co/n665ou3PRv
Viewing enriched Twitter post
I alluded to this a few tweets ago but just pushed up a shortish blog on a subtle feature of CLC work stealing that makes cuda-graphable grouped_gemm possible with this scheduling mode: https://t.co/n665ou3PRv
{
"media": [
{
"url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2051063573703786709/media_0.jpg",
"media_url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2051063573703786709/media_0.jpg",
"type": "photo",
"filename": "media_0.jpg"
}
],
"processed_at": "2026-05-11T22:39:40.801787",
"pipeline_version": "2.0"
} {
"type": "tweet",
"id": "2051063573703786709",
"url": "https://x.com/drisspg/status/2051063573703786709",
"twitterUrl": "https://twitter.com/drisspg/status/2051063573703786709",
"text": "I alluded to this a few tweets ago but just pushed up a shortish blog on a subtle feature of CLC work stealing that makes cuda-graphable grouped_gemm possible with this scheduling mode:\nhttps://t.co/n665ou3PRv",
"source": "Twitter for iPhone",
"retweetCount": 8,
"replyCount": 4,
"likeCount": 46,
"quoteCount": 1,
"viewCount": 5270,
"createdAt": "Sun May 03 22:17:17 +0000 2026",
"lang": "en",
"bookmarkCount": 26,
"isReply": false,
"inReplyToId": null,
"conversationId": "2051063573703786709",
"displayTextRange": [
0,
209
],
"inReplyToUserId": null,
"inReplyToUsername": null,
"author": {
"type": "user",
"userName": "drisspg",
"url": "https://x.com/drisspg",
"twitterUrl": "https://twitter.com/drisspg",
"id": "1734997526778970112",
"name": "driss guessous",
"isVerified": false,
"isBlueVerified": false,
"verifiedType": null,
"profilePicture": "https://pbs.twimg.com/profile_images/1735301929519951872/dBy44OnX_normal.jpg",
"coverPicture": "",
"description": "",
"location": "",
"followers": 1460,
"following": 245,
"status": "",
"canDm": false,
"canMediaTag": true,
"createdAt": "Wed Dec 13 18:03:55 +0000 2023",
"entities": {
"description": {
"urls": []
},
"url": {}
},
"fastFollowersCount": 0,
"favouritesCount": 332,
"hasCustomTimelines": true,
"isTranslator": false,
"mediaCount": 71,
"statusesCount": 456,
"withheldInCountries": [],
"affiliatesHighlightedLabel": {},
"possiblySensitive": false,
"pinnedTweetIds": [],
"profile_bio": {
"description": "bytes and nuggets @pytorch\nhttps://t.co/gWVJmW741f",
"entities": {
"description": {
"urls": [
{
"display_url": "drisspg.github.io/nuggets/",
"expanded_url": "https://drisspg.github.io/nuggets/",
"indices": [
27,
50
],
"url": "https://t.co/gWVJmW741f"
}
],
"user_mentions": [
{
"id_str": "",
"indices": [
18,
26
],
"name": "",
"screen_name": "pytorch"
}
]
},
"url": {
"urls": [
{
"display_url": "github.com/drisspg",
"expanded_url": "https://github.com/drisspg",
"indices": [
0,
23
],
"url": "https://t.co/mio2YiKc1s"
}
]
}
}
},
"isAutomated": false,
"automatedBy": null
},
"extendedEntities": {},
"card": null,
"place": {},
"entities": {
"hashtags": [],
"symbols": [],
"timestamps": [],
"urls": [
{
"display_url": "drisspg.github.io/nuggets/A-Taleβ¦",
"expanded_url": "https://drisspg.github.io/nuggets/A-Tale-of-Two-Schedulers",
"indices": [
186,
209
],
"url": "https://t.co/n665ou3PRv"
}
],
"user_mentions": []
},
"quoted_tweet": null,
"retweeted_tweet": null,
"isLimitedReply": false,
"communityInfo": null,
"article": null
}