Viewing enriched Twitter post
By combining MAX software optimizations + AMD MI355's higher GPU memory + @TensorWave's liquid-cooled infrastructure we achieved ~2× greater inference throughput on MI355 clusters and 40-60% reduction in inference costs. Full methodology and benchmarks: https://t.co/XegRDVrvvm
{
"media": [
{
"type": "photo",
"url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/1998830158384619578/media_0.jpg?",
"filename": "media_0.jpg"
}
],
"processed_at": "2025-12-10T19:57:13.290762",
"pipeline_version": "2.0"
}{
"type": "tweet",
"id": "1998830158384619578",
"url": "https://x.com/Modular/status/1998830158384619578",
"twitterUrl": "https://twitter.com/Modular/status/1998830158384619578",
"text": "By combining MAX software optimizations + AMD MI355's higher GPU memory + @TensorWave's liquid-cooled infrastructure we achieved ~2× greater inference throughput on MI355 clusters and 40-60% reduction in inference costs.\n\nFull methodology and benchmarks: https://t.co/XegRDVrvvm",
"source": "Twitter for iPhone",
"retweetCount": 0,
"replyCount": 0,
"likeCount": 1,
"quoteCount": 0,
"viewCount": 182,
"createdAt": "Wed Dec 10 19:00:20 +0000 2025",
"lang": "en",
"bookmarkCount": 0,
"isReply": true,
"inReplyToId": "1998830146648944791",
"conversationId": "1998830110410264804",
"displayTextRange": [
0,
278
],
"inReplyToUserId": null,
"inReplyToUsername": null,
"author": {
"type": "user",
"userName": "Modular",
"url": "https://x.com/Modular",
"twitterUrl": "https://twitter.com/Modular",
"id": "1483918307484848132",
"name": "Modular",
"isVerified": false,
"isBlueVerified": true,
"verifiedType": "Business",
"profilePicture": "https://pbs.twimg.com/profile_images/1786875652656025600/mp6VADd5_normal.png",
"coverPicture": "https://pbs.twimg.com/profile_banners/1483918307484848132/1714859329",
"description": "Building AI’s unified compute layer. We are hiring → https://t.co/cPTAes0HMt 🚀",
"location": "",
"followers": 20759,
"following": 2,
"status": "",
"canDm": false,
"canMediaTag": true,
"createdAt": "Wed Jan 19 21:46:38 +0000 2022",
"entities": {
"description": {
"urls": [
{
"display_url": "modular.com/careers",
"expanded_url": "http://modular.com/careers",
"url": "https://t.co/cPTAes0HMt",
"indices": [
53,
76
]
}
]
},
"url": {
"urls": [
{
"display_url": "modular.com",
"expanded_url": "https://www.modular.com",
"url": "https://t.co/dFAH0NVA0N",
"indices": [
0,
23
]
}
]
}
},
"fastFollowersCount": 0,
"favouritesCount": 672,
"hasCustomTimelines": false,
"isTranslator": false,
"mediaCount": 309,
"statusesCount": 1009,
"withheldInCountries": [],
"affiliatesHighlightedLabel": {},
"possiblySensitive": false,
"pinnedTweetIds": [
"1970881293933273524"
],
"profile_bio": {},
"isAutomated": false,
"automatedBy": null
},
"extendedEntities": {},
"card": {
"binding_values": [
{
"key": "description",
"value": {
"string_value": "In a recent talk, Nikhil Gupta, ML Engineer at TensorWave, walked through two company case studies that show just how far you can push training and inference when you pair modern AMD hardware with...",
"type": "STRING"
}
},
{
"key": "domain",
"value": {
"string_value": "tensorwave.com",
"type": "STRING"
}
},
{
"key": "vanity_url",
"value": {
"scribe_key": "vanity_url",
"string_value": "tensorwave.com",
"type": "STRING"
}
},
{
"key": "title",
"value": {
"string_value": "Real AI Workloads on AMD GPUs: Inference, Training, and Scaling",
"type": "STRING"
}
},
{
"key": "card_url",
"value": {
"scribe_key": "card_url",
"string_value": "https://t.co/XegRDVrvvm",
"type": "STRING"
}
}
],
"card_platform": {
"platform": {
"audience": {
"name": "production"
},
"device": {
"name": "Android",
"version": "12"
}
}
},
"name": "summary_large_image",
"url": "https://t.co/XegRDVrvvm",
"user_refs_results": []
},
"place": {},
"entities": {
"hashtags": [],
"symbols": [],
"timestamps": [],
"urls": [
{
"display_url": "tensorwave.com/blog/real-ai-w…",
"expanded_url": "https://tensorwave.com/blog/real-ai-workloads-on-amd-gpus-inference-training-and-scaling",
"url": "https://t.co/XegRDVrvvm",
"indices": [
255,
278
]
}
],
"user_mentions": [
{
"id_str": "1731183443395112960",
"name": "TensorWave",
"screen_name": "tensorwave",
"indices": [
74,
85
]
}
]
},
"quoted_tweet": null,
"retweeted_tweet": null,
"article": null
}