Viewing enriched Twitter post
Join us Tue 5/5: #DeepSeek-V4's hybrid attention + sparse MoE reduces KV cache up to 90%, enabling 1M-token context. We'll cover why that makes it great for agentic workflows, what it took to serve at scale, and how to build with it. Hear from @realDanFu @JueWANG26088228 @ZainHasan6 and @zhyncs42 → https://t.co/9mkBnymJoQ
{
"media": [
{
"url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2049940598917087262/media_0.jpg",
"media_url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2049940598917087262/media_0.jpg",
"type": "photo",
"filename": "media_0.jpg"
}
],
"processed_at": "2026-05-11T22:39:40.105344",
"pipeline_version": "2.0"
}{
"type": "tweet",
"id": "2049940598917087262",
"url": "https://x.com/togethercompute/status/2049940598917087262",
"twitterUrl": "https://twitter.com/togethercompute/status/2049940598917087262",
"text": "Join us Tue 5/5: #DeepSeek-V4's hybrid attention + sparse MoE reduces KV cache up to 90%, enabling 1M-token context. \n\nWe'll cover why that makes it great for agentic workflows, what it took to serve at scale, and how to build with it. Hear from @realDanFu @JueWANG26088228 @ZainHasan6 and @zhyncs42 → https://t.co/9mkBnymJoQ",
"source": "Twitter for iPhone",
"retweetCount": 7,
"replyCount": 7,
"likeCount": 23,
"quoteCount": 2,
"viewCount": 8845,
"createdAt": "Thu Apr 30 19:54:59 +0000 2026",
"lang": "en",
"bookmarkCount": 6,
"isReply": false,
"inReplyToId": null,
"conversationId": "2049940598917087262",
"displayTextRange": [
0,
273
],
"inReplyToUserId": null,
"inReplyToUsername": null,
"author": {
"type": "user",
"userName": "togethercompute",
"url": "https://x.com/togethercompute",
"twitterUrl": "https://twitter.com/togethercompute",
"id": "1592266692528197632",
"name": "Together AI",
"isVerified": false,
"isBlueVerified": false,
"verifiedType": "Business",
"profilePicture": "https://pbs.twimg.com/profile_images/2028879663221882886/sMzEKnKc_normal.jpg",
"coverPicture": "https://pbs.twimg.com/profile_banners/1592266692528197632/1772467486",
"description": "",
"location": "San Francisco, CA",
"followers": 55063,
"following": 397,
"status": "",
"canDm": false,
"canMediaTag": true,
"createdAt": "Mon Nov 14 21:23:18 +0000 2022",
"entities": {
"description": {
"urls": []
},
"url": {}
},
"fastFollowersCount": 0,
"favouritesCount": 2095,
"hasCustomTimelines": true,
"isTranslator": false,
"mediaCount": 799,
"statusesCount": 2662,
"withheldInCountries": [],
"affiliatesHighlightedLabel": {},
"possiblySensitive": false,
"pinnedTweetIds": [
"2047743446522224987"
],
"profile_bio": {
"description": "Accelerate inference, model shaping, and pre-training on a research-optimized platform.",
"entities": {
"description": {},
"url": {
"urls": [
{
"display_url": "together.ai",
"expanded_url": "http://together.ai",
"indices": [
0,
23
],
"url": "https://t.co/ymnk7vEStt"
}
]
}
}
},
"isAutomated": false,
"automatedBy": null
},
"extendedEntities": {
"media": [
{
"allow_download_status": {
"allow_download": true
},
"display_url": "pic.twitter.com/Mejs8QnQFq",
"expanded_url": "https://twitter.com/togethercompute/status/2049940598917087262/photo/1",
"ext_media_availability": {
"status": "Available"
},
"features": {
"large": {
"faces": [
{
"h": 39,
"w": 39,
"x": 637,
"y": 248
},
{
"h": 37,
"w": 37,
"x": 636,
"y": 328
},
{
"h": 43,
"w": 43,
"x": 635,
"y": 404
},
{
"h": 66,
"w": 66,
"x": 712,
"y": 235
}
]
},
"orig": {
"faces": [
{
"h": 39,
"w": 39,
"x": 637,
"y": 248
},
{
"h": 37,
"w": 37,
"x": 636,
"y": 328
},
{
"h": 43,
"w": 43,
"x": 635,
"y": 404
},
{
"h": 66,
"w": 66,
"x": 712,
"y": 235
}
]
}
},
"id_str": "2049940458869321728",
"indices": [
274,
297
],
"media_key": "3_2049940458869321728",
"media_results": {
"id": "QXBpTWVkaWFSZXN1bHRzOgwAAQoAARxy2fx9m3AACgACHHLaHRkawB4AAA==",
"result": {
"__typename": "ApiMedia",
"id": "QXBpTWVkaWE6DAABCgABHHLZ/H2bcAAKAAIcctodGRrAHgAA",
"media_key": "3_2049940458869321728"
}
},
"media_url_https": "https://pbs.twimg.com/media/HHLZ_H2bcAAfWqf.jpg",
"original_info": {
"focus_rects": [
{
"h": 630,
"w": 1125,
"x": 0,
"y": 0
},
{
"h": 630,
"w": 630,
"x": 15,
"y": 0
},
{
"h": 630,
"w": 553,
"x": 54,
"y": 0
},
{
"h": 630,
"w": 315,
"x": 173,
"y": 0
},
{
"h": 630,
"w": 1200,
"x": 0,
"y": 0
}
],
"height": 630,
"width": 1200
},
"sizes": {
"large": {
"h": 630,
"w": 1200
}
},
"type": "photo",
"url": "https://t.co/Mejs8QnQFq"
}
]
},
"card": null,
"place": {},
"entities": {
"hashtags": [
{
"indices": [
17,
26
],
"text": "DeepSeek"
}
],
"symbols": [],
"urls": [
{
"display_url": "togetherai.link/ds-v4-x",
"expanded_url": "https://togetherai.link/ds-v4-x",
"indices": [
303,
326
],
"url": "https://t.co/9mkBnymJoQ"
}
],
"user_mentions": [
{
"id_str": "1173687463790829568",
"indices": [
246,
256
],
"name": "Dan Fu",
"screen_name": "realDanFu"
},
{
"id_str": "1051706523724857344",
"indices": [
257,
273
],
"name": "Jue WANG",
"screen_name": "JueWANG26088228"
},
{
"id_str": "781542714",
"indices": [
274,
285
],
"name": "Zain",
"screen_name": "ZainHasan6"
},
{
"id_str": "1760723449503469569",
"indices": [
290,
299
],
"name": "zhyncs",
"screen_name": "zhyncs42"
}
]
},
"quoted_tweet": null,
"retweeted_tweet": null,
"isLimitedReply": false,
"communityInfo": null,
"article": null
}