@winglian
@art_zucker @Tu7uruu Does paged attention support optimized backwards? If not, can it switch between attn implementations for inference vs training?
Viewing enriched Twitter post
@art_zucker @Tu7uruu Does paged attention support optimized backwards? If not, can it switch between attn implementations for inference vs training?
{
"score": 0.38,
"score_components": {
"author": 0.09,
"engagement": 0.0,
"quality": 0.08000000000000002,
"source": 0.135,
"nlp": 0.05,
"recency": 0.025
},
"scored_at": "2026-03-14T16:07:20.829468",
"import_source": "api_import",
"source_tagged_at": "2026-03-14T16:07:20.829482",
"enriched": true,
"enriched_at": "2026-03-14T16:07:20.829485"
} {
"type": "tweet",
"id": "2032850363385012363",
"url": "https://x.com/winglian/status/2032850363385012363",
"twitterUrl": "https://twitter.com/winglian/status/2032850363385012363",
"text": "@art_zucker @Tu7uruu Does paged attention support optimized backwards? If not, can it switch between attn implementations for inference vs training?",
"source": "Twitter for iPhone",
"retweetCount": 0,
"replyCount": 0,
"likeCount": 0,
"quoteCount": 0,
"viewCount": 7,
"createdAt": "Sat Mar 14 16:04:29 +0000 2026",
"lang": "en",
"bookmarkCount": 0,
"isReply": true,
"inReplyToId": "2032729209584370160",
"conversationId": "2032729209584370160",
"displayTextRange": [
21,
148
],
"inReplyToUserId": "1444622906756063235",
"inReplyToUsername": "art_zucker",
"author": {
"type": "user",
"userName": "winglian",
"url": "https://x.com/winglian",
"twitterUrl": "https://twitter.com/winglian",
"id": "24802509",
"name": "Wing Lian (caseus)",
"isVerified": false,
"isBlueVerified": true,
"verifiedType": null,
"profilePicture": "https://pbs.twimg.com/profile_images/1709990043664715778/FZmSZJaK_normal.jpg",
"coverPicture": "https://pbs.twimg.com/profile_banners/24802509/1403302292",
"description": "",
"location": "Annapolis, MD",
"followers": 10594,
"following": 1839,
"status": "",
"canDm": true,
"canMediaTag": true,
"createdAt": "Tue Mar 17 00:12:21 +0000 2009",
"entities": {
"description": {
"urls": []
},
"url": {}
},
"fastFollowersCount": 0,
"favouritesCount": 3273,
"hasCustomTimelines": true,
"isTranslator": false,
"mediaCount": 161,
"statusesCount": 2883,
"withheldInCountries": [],
"affiliatesHighlightedLabel": {},
"possiblySensitive": false,
"pinnedTweetIds": [],
"profile_bio": {
"description": "@axolotl_ai OSS maintainer. Axolotl AI founder. AI/ML tinkerer. Building tools for everyone.",
"entities": {
"description": {
"hashtags": [],
"symbols": [],
"urls": [],
"user_mentions": [
{
"id_str": "0",
"indices": [
0,
11
],
"name": "",
"screen_name": "axolotl_ai"
}
]
},
"url": {
"urls": [
{
"display_url": "github.com/winglian/",
"expanded_url": "https://github.com/winglian/",
"indices": [
0,
23
],
"url": "https://t.co/Ym8RB0dslS"
}
]
}
}
},
"isAutomated": false,
"automatedBy": null
},
"extendedEntities": {},
"card": null,
"place": {},
"entities": {
"hashtags": [],
"symbols": [],
"timestamps": [],
"urls": [],
"user_mentions": [
{
"id_str": "1444622906756063235",
"indices": [
0,
11
],
"name": "Arthur Zucker",
"screen_name": "art_zucker"
},
{
"id_str": "2350034150",
"indices": [
12,
20
],
"name": "steven",
"screen_name": "Tu7uruu"
}
]
},
"quoted_tweet": null,
"retweeted_tweet": null,
"isLimitedReply": false,
"article": null
}