Viewing enriched Twitter post
Need to optimize applications with large models and stretched memory resources? Learn how to accelerate large-scale LLM inference and Cache Offload with CPU-GPU Memory Sharing in NVIDIA’s recent developer tech blog: 📎: https://t.co/eyx4DLi6ta #PyTorch #OpenSourceAI #AI #Inference #Innovation
{
"media": [
{
"type": "photo",
"url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/1991262100023353463/media_0.jpg?",
"filename": "media_0.jpg"
}
],
"processed_at": "2025-11-27T21:08:33.375719",
"pipeline_version": "2.0"
}{
"type": "tweet",
"id": "1991262100023353463",
"url": "https://x.com/PyTorch/status/1991262100023353463",
"twitterUrl": "https://twitter.com/PyTorch/status/1991262100023353463",
"text": "Need to optimize applications with large models and stretched memory resources?\n\nLearn how to accelerate large-scale LLM inference and Cache Offload with CPU-GPU Memory Sharing in NVIDIA’s recent developer tech blog:\n\n📎: https://t.co/eyx4DLi6ta\n\n#PyTorch #OpenSourceAI #AI #Inference #Innovation",
"source": "Twitter for iPhone",
"retweetCount": 12,
"replyCount": 3,
"likeCount": 101,
"quoteCount": 0,
"viewCount": 11606,
"createdAt": "Wed Nov 19 21:47:35 +0000 2025",
"lang": "en",
"bookmarkCount": 58,
"isReply": false,
"inReplyToId": null,
"conversationId": "1991262100023353463",
"displayTextRange": [
0,
273
],
"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": 462518,
"following": 78,
"status": "",
"canDm": false,
"canMediaTag": true,
"createdAt": "Fri Sep 16 00:56:26 +0000 2016",
"entities": {
"description": {
"urls": []
},
"url": {}
},
"fastFollowersCount": 0,
"favouritesCount": 843,
"hasCustomTimelines": true,
"isTranslator": false,
"mediaCount": 1229,
"statusesCount": 2947,
"withheldInCountries": [],
"affiliatesHighlightedLabel": {},
"possiblySensitive": false,
"pinnedTweetIds": [
"1993494986810163396"
],
"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": {},
"card": {
"binding_values": [
{
"key": "photo_image_full_size_large",
"value": {
"image_value": {
"alt": "Decorative image.",
"height": 419,
"url": "https://pbs.twimg.com/card_img/1993798976408043521/E8UD_Tdy?format=jpg&name=800x419",
"width": 800
}
}
},
{
"key": "thumbnail_image",
"value": {
"image_value": {
"alt": "Decorative image.",
"height": 150,
"url": "https://pbs.twimg.com/card_img/1993798976408043521/E8UD_Tdy?format=jpg&name=280x150",
"width": 267
}
}
},
{
"key": "description",
"value": {
"string_value": "Large Language Models (LLMs) are at the forefront of AI innovation, but their massive size can complicate inference efficiency. Models such as Llama 3 70B and Llama 4 Scout 109B may require more…"
}
},
{
"key": "domain",
"value": {
"string_value": "developer.nvidia.com"
}
},
{
"key": "thumbnail_image_large",
"value": {
"image_value": {
"alt": "Decorative image.",
"height": 320,
"url": "https://pbs.twimg.com/card_img/1993798976408043521/E8UD_Tdy?format=jpg&name=800x320_1",
"width": 569
}
}
},
{
"key": "summary_photo_image_small",
"value": {
"image_value": {
"alt": "Decorative image.",
"height": 202,
"url": "https://pbs.twimg.com/card_img/1993798976408043521/E8UD_Tdy?format=jpg&name=386x202",
"width": 386
}
}
},
{
"key": "thumbnail_image_original",
"value": {
"image_value": {
"alt": "Decorative image.",
"height": 1080,
"url": "https://pbs.twimg.com/card_img/1993798976408043521/E8UD_Tdy?format=jpg&name=orig",
"width": 1920
}
}
},
{
"key": "photo_image_full_size_small",
"value": {
"image_value": {
"alt": "Decorative image.",
"height": 202,
"url": "https://pbs.twimg.com/card_img/1993798976408043521/E8UD_Tdy?format=jpg&name=386x202",
"width": 386
}
}
},
{
"key": "summary_photo_image_large",
"value": {
"image_value": {
"alt": "Decorative image.",
"height": 419,
"url": "https://pbs.twimg.com/card_img/1993798976408043521/E8UD_Tdy?format=jpg&name=800x419",
"width": 800
}
}
},
{
"key": "thumbnail_image_small",
"value": {
"image_value": {
"alt": "Decorative image.",
"height": 81,
"url": "https://pbs.twimg.com/card_img/1993798976408043521/E8UD_Tdy?format=jpg&name=144x144",
"width": 144
}
}
},
{
"key": "thumbnail_image_x_large",
"value": {
"image_value": {
"alt": "Decorative image.",
"height": 1080,
"url": "https://pbs.twimg.com/card_img/1993798976408043521/E8UD_Tdy?format=png&name=2048x2048_2_exp",
"width": 1920
}
}
},
{
"key": "photo_image_full_size_original",
"value": {
"image_value": {
"alt": "Decorative image.",
"height": 1080,
"url": "https://pbs.twimg.com/card_img/1993798976408043521/E8UD_Tdy?format=jpg&name=orig",
"width": 1920
}
}
},
{
"key": "photo_image_full_size_alt_text",
"value": {
"string_value": "Decorative image."
}
},
{
"key": "vanity_url",
"value": {
"scribe_key": "vanity_url",
"string_value": "developer.nvidia.com"
}
},
{
"key": "photo_image_full_size",
"value": {
"image_value": {
"alt": "Decorative image.",
"height": 314,
"url": "https://pbs.twimg.com/card_img/1993798976408043521/E8UD_Tdy?format=jpg&name=600x314",
"width": 600
}
}
},
{
"key": "summary_photo_image_alt_text",
"value": {
"string_value": "Decorative image."
}
},
{
"key": "thumbnail_image_color",
"value": {
"image_color_value": {
"palette": [
{
"percentage": 88.87,
"rgb": {
"blue": 95,
"green": 55,
"red": 26
}
},
{
"percentage": 3.45,
"rgb": {
"blue": 54,
"green": 185,
"red": 130
}
},
{
"percentage": 1.73,
"rgb": {
"blue": 76,
"green": 147,
"red": 89
}
},
{
"percentage": 1.38,
"rgb": {
"blue": 103,
"green": 123,
"red": 82
}
},
{
"percentage": 0.75,
"rgb": {
"blue": 217,
"green": 241,
"red": 227
}
}
]
}
}
},
{
"key": "title",
"value": {
"string_value": "Accelerate Large-Scale LLM Inference and KV Cache Offload with CPU-GPU Memory Sharing | NVIDIA..."
}
},
{
"key": "summary_photo_image_color",
"value": {
"image_color_value": {
"palette": [
{
"percentage": 88.87,
"rgb": {
"blue": 95,
"green": 55,
"red": 26
}
},
{
"percentage": 3.45,
"rgb": {
"blue": 54,
"green": 185,
"red": 130
}
},
{
"percentage": 1.73,
"rgb": {
"blue": 76,
"green": 147,
"red": 89
}
},
{
"percentage": 1.38,
"rgb": {
"blue": 103,
"green": 123,
"red": 82
}
},
{
"percentage": 0.75,
"rgb": {
"blue": 217,
"green": 241,
"red": 227
}
}
]
}
}
},
{
"key": "summary_photo_image_x_large",
"value": {
"image_value": {
"alt": "Decorative image.",
"height": 1080,
"url": "https://pbs.twimg.com/card_img/1993798976408043521/E8UD_Tdy?format=png&name=2048x2048_2_exp",
"width": 1920
}
}
},
{
"key": "summary_photo_image",
"value": {
"image_value": {
"alt": "Decorative image.",
"height": 314,
"url": "https://pbs.twimg.com/card_img/1993798976408043521/E8UD_Tdy?format=jpg&name=600x314",
"width": 600
}
}
},
{
"key": "photo_image_full_size_color",
"value": {
"image_color_value": {
"palette": [
{
"percentage": 88.87,
"rgb": {
"blue": 95,
"green": 55,
"red": 26
}
},
{
"percentage": 3.45,
"rgb": {
"blue": 54,
"green": 185,
"red": 130
}
},
{
"percentage": 1.73,
"rgb": {
"blue": 76,
"green": 147,
"red": 89
}
},
{
"percentage": 1.38,
"rgb": {
"blue": 103,
"green": 123,
"red": 82
}
},
{
"percentage": 0.75,
"rgb": {
"blue": 217,
"green": 241,
"red": 227
}
}
]
}
}
},
{
"key": "photo_image_full_size_x_large",
"value": {
"image_value": {
"alt": "Decorative image.",
"height": 1080,
"url": "https://pbs.twimg.com/card_img/1993798976408043521/E8UD_Tdy?format=png&name=2048x2048_2_exp",
"width": 1920
}
}
},
{
"key": "card_url",
"value": {
"scribe_key": "card_url",
"string_value": "https://t.co/QIhGTHV8xV"
}
},
{
"key": "summary_photo_image_original",
"value": {
"image_value": {
"alt": "Decorative image.",
"height": 1080,
"url": "https://pbs.twimg.com/card_img/1993798976408043521/E8UD_Tdy?format=jpg&name=orig",
"width": 1920
}
}
}
],
"card_platform": {
"platform": {
"audience": {
"name": "production"
},
"device": {
"name": "iPhone",
"version": "13"
}
}
},
"name": "summary_large_image",
"url": "https://t.co/QIhGTHV8xV"
},
"place": {},
"entities": {
"hashtags": [
{
"indices": [
246,
254
],
"text": "PyTorch"
},
{
"indices": [
255,
268
],
"text": "OpenSourceAI"
},
{
"indices": [
269,
272
],
"text": "AI"
},
{
"indices": [
273,
283
],
"text": "Inference"
},
{
"indices": [
284,
295
],
"text": "Innovation"
}
],
"urls": [
{
"display_url": "hubs.la/Q03V7v_q0",
"expanded_url": "https://hubs.la/Q03V7v_q0",
"indices": [
221,
244
],
"url": "https://t.co/eyx4DLi6ta"
}
]
},
"quoted_tweet": null,
"retweeted_tweet": null,
"isLimitedReply": false,
"article": null
}