@PyTorch
Scaling RL for LLMs is hard. The #PyTorch team at Meta open sourced torchforge and shares #ReinforcementLearning lessons from evaluating it with Weaver on a 512 GPU cluster. š https://t.co/1iayWOGU26 https://t.co/cGTUg0hfYn
Viewing enriched Twitter post
Scaling RL for LLMs is hard. The #PyTorch team at Meta open sourced torchforge and shares #ReinforcementLearning lessons from evaluating it with Weaver on a 512 GPU cluster. š https://t.co/1iayWOGU26 https://t.co/cGTUg0hfYn
{
"media": [
{
"type": "photo",
"url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2009730563532349575/media_0.jpg?",
"filename": "media_0.jpg"
}
],
"processed_at": "2026-01-18T19:38:14.148148",
"pipeline_version": "2.0"
} {
"type": "tweet",
"id": "2009730563532349575",
"url": "https://x.com/PyTorch/status/2009730563532349575",
"twitterUrl": "https://twitter.com/PyTorch/status/2009730563532349575",
"text": "Scaling RL for LLMs is hard. The #PyTorch team at Meta open sourced torchforge and shares #ReinforcementLearning lessons from evaluating it with Weaver on a 512 GPU cluster. \n\nš https://t.co/1iayWOGU26 https://t.co/cGTUg0hfYn",
"source": "Twitter for iPhone",
"retweetCount": 15,
"replyCount": 3,
"likeCount": 84,
"quoteCount": 2,
"viewCount": 10365,
"createdAt": "Fri Jan 09 20:54:39 +0000 2026",
"lang": "en",
"bookmarkCount": 39,
"isReply": false,
"inReplyToId": null,
"conversationId": "2009730563532349575",
"displayTextRange": [
0,
201
],
"inReplyToUserId": null,
"inReplyToUsername": null,
"author": {
"type": "user",
"userName": "PyTorch",
"url": "https://x.com/PyTorch",
"twitterUrl": "https://twitter.com/PyTorch",
"id": "776585502606721024",
"name": "PyTorch",
"isVerified": false,
"isBlueVerified": true,
"verifiedType": null,
"profilePicture": "https://pbs.twimg.com/profile_images/1813965160702451712/yXV1vRhr_normal.jpg",
"coverPicture": "https://pbs.twimg.com/profile_banners/776585502606721024/1761575044",
"description": "",
"location": "",
"followers": 470158,
"following": 81,
"status": "",
"canDm": false,
"canMediaTag": true,
"createdAt": "Fri Sep 16 00:56:26 +0000 2016",
"entities": {
"description": {
"urls": []
},
"url": {}
},
"fastFollowersCount": 0,
"favouritesCount": 838,
"hasCustomTimelines": true,
"isTranslator": false,
"mediaCount": 1271,
"statusesCount": 2996,
"withheldInCountries": [],
"affiliatesHighlightedLabel": {},
"possiblySensitive": false,
"pinnedTweetIds": [],
"profile_bio": {
"description": "Tensors and neural networks in Python with strong hardware acceleration. PyTorch is an open source project at the Linux Foundation. #PyTorchFoundation",
"entities": {
"description": {
"hashtags": [
{
"indices": [
132,
150
],
"text": "PyTorchFoundation"
}
]
},
"url": {
"urls": [
{
"display_url": "pytorch.org",
"expanded_url": "http://pytorch.org",
"indices": [
0,
23
],
"url": "https://t.co/6SwTBhUwTJ"
}
]
}
}
},
"isAutomated": false,
"automatedBy": null
},
"extendedEntities": {
"media": [
{
"display_url": "pic.twitter.com/cGTUg0hfYn",
"expanded_url": "https://twitter.com/PyTorch/status/2009730563532349575/photo/1",
"ext_media_availability": {
"status": "Available"
},
"features": {
"large": {
"faces": [
{
"h": 75,
"w": 75,
"x": 1267,
"y": 676
},
{
"h": 82,
"w": 82,
"x": 480,
"y": 508
}
]
},
"orig": {
"faces": [
{
"h": 75,
"w": 75,
"x": 1267,
"y": 676
},
{
"h": 82,
"w": 82,
"x": 480,
"y": 508
}
]
}
},
"id_str": "2009730559874867201",
"indices": [
202,
225
],
"media_key": "3_2009730559874867201",
"media_results": {
"id": "QXBpTWVkaWFSZXN1bHRzOgwAAQoAARvj/0vTlqABCgACG+P/TK2XYIcAAA==",
"result": {
"__typename": "ApiMedia",
"id": "QXBpTWVkaWE6DAABCgABG+P/S9OWoAEKAAIb4/9MrZdghwAA",
"media_key": "3_2009730559874867201"
}
},
"media_url_https": "https://pbs.twimg.com/media/G-P_S9OWoAEvBQl.jpg",
"original_info": {
"focus_rects": [
{
"h": 1075,
"w": 1920,
"x": 0,
"y": 0
},
{
"h": 1080,
"w": 1080,
"x": 0,
"y": 0
},
{
"h": 1080,
"w": 947,
"x": 0,
"y": 0
},
{
"h": 1080,
"w": 540,
"x": 162,
"y": 0
},
{
"h": 1080,
"w": 1920,
"x": 0,
"y": 0
}
],
"height": 1080,
"width": 1920
},
"sizes": {
"large": {
"h": 1080,
"w": 1920
}
},
"type": "photo",
"url": "https://t.co/cGTUg0hfYn"
}
]
},
"card": null,
"place": {},
"entities": {
"hashtags": [
{
"indices": [
33,
41
],
"text": "PyTorch"
},
{
"indices": [
90,
112
],
"text": "ReinforcementLearning"
}
],
"urls": [
{
"display_url": "hubs.la/Q03-fZs_0",
"expanded_url": "https://hubs.la/Q03-fZs_0",
"indices": [
178,
201
],
"url": "https://t.co/1iayWOGU26"
}
]
},
"quoted_tweet": null,
"retweeted_tweet": null,
"isLimitedReply": false,
"article": null
}