Viewing enriched Twitter post
NVIDIA highlights vLLM as one of the open source frameworks available for serving Step 3.7 Flash, StepFun's 198B-parameter multimodal Mixture-of-Experts model. NVIDIA's developer blog covers deployment, inference, and fine-tuning workflows for the model, which supports image and video inputs and a 256K context window. Read more: https://t.co/A6VftfrYyK
{
"media": [
{
"url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2069527201712656822/media_0.jpg",
"media_url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2069527201712656822/media_0.jpg",
"type": "photo",
"filename": "media_0.jpg"
}
],
"processed_at": "2026-06-23T21:19:12.061712",
"pipeline_version": "2.0"
}{
"type": "tweet",
"id": "2069527201712656822",
"url": "https://x.com/PyTorch/status/2069527201712656822",
"twitterUrl": "https://twitter.com/PyTorch/status/2069527201712656822",
"text": "NVIDIA highlights vLLM as one of the open source frameworks available for serving Step 3.7 Flash, StepFun's 198B-parameter multimodal Mixture-of-Experts model.\n\nNVIDIA's developer blog covers deployment, inference, and fine-tuning workflows for the model, which supports image and video inputs and a 256K context window.\n\nRead more: https://t.co/A6VftfrYyK",
"source": "Twitter for iPhone",
"retweetCount": 0,
"replyCount": 1,
"likeCount": 3,
"quoteCount": 0,
"viewCount": 1155,
"createdAt": "Tue Jun 23 21:05:09 +0000 2026",
"lang": "en",
"bookmarkCount": 2,
"isReply": false,
"inReplyToId": null,
"conversationId": "2069527201712656822",
"displayTextRange": [
0,
280
],
"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": 498684,
"following": 87,
"status": "",
"canDm": false,
"canMediaTag": true,
"createdAt": "Fri Sep 16 00:56:26 +0000 2016",
"entities": {
"description": {
"urls": []
},
"url": {}
},
"fastFollowersCount": 0,
"favouritesCount": 954,
"hasCustomTimelines": true,
"isTranslator": false,
"mediaCount": 1514,
"statusesCount": 3351,
"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": {},
"card": {
"binding_values": [
{
"key": "photo_image_full_size_large",
"value": {
"image_value": {
"height": 419,
"url": "https://pbs.twimg.com/card_img/2069527208830345216/znw4vBjI?format=jpg&name=800x419",
"width": 800
}
}
},
{
"key": "thumbnail_image",
"value": {
"image_value": {
"height": 150,
"url": "https://pbs.twimg.com/card_img/2069527208830345216/znw4vBjI?format=jpg&name=280x150",
"width": 267
}
}
},
{
"key": "description",
"value": {
"string_value": "AI applications are moving beyond text generation to multimodal systems that can perceive, search, and reason across images, documents, video, and language in real time—turning fragmented information…"
}
},
{
"key": "domain",
"value": {
"string_value": "developer.nvidia.com"
}
},
{
"key": "thumbnail_image_large",
"value": {
"image_value": {
"height": 320,
"url": "https://pbs.twimg.com/card_img/2069527208830345216/znw4vBjI?format=jpg&name=800x320_1",
"width": 569
}
}
},
{
"key": "summary_photo_image_small",
"value": {
"image_value": {
"height": 202,
"url": "https://pbs.twimg.com/card_img/2069527208830345216/znw4vBjI?format=jpg&name=386x202",
"width": 386
}
}
},
{
"key": "thumbnail_image_original",
"value": {
"image_value": {
"height": 1080,
"url": "https://pbs.twimg.com/card_img/2069527208830345216/znw4vBjI?format=jpg&name=orig",
"width": 1920
}
}
},
{
"key": "photo_image_full_size_small",
"value": {
"image_value": {
"height": 202,
"url": "https://pbs.twimg.com/card_img/2069527208830345216/znw4vBjI?format=jpg&name=386x202",
"width": 386
}
}
},
{
"key": "summary_photo_image_large",
"value": {
"image_value": {
"height": 419,
"url": "https://pbs.twimg.com/card_img/2069527208830345216/znw4vBjI?format=jpg&name=800x419",
"width": 800
}
}
},
{
"key": "thumbnail_image_small",
"value": {
"image_value": {
"height": 81,
"url": "https://pbs.twimg.com/card_img/2069527208830345216/znw4vBjI?format=jpg&name=144x144",
"width": 144
}
}
},
{
"key": "thumbnail_image_x_large",
"value": {
"image_value": {
"height": 1080,
"url": "https://pbs.twimg.com/card_img/2069527208830345216/znw4vBjI?format=png&name=2048x2048_2_exp",
"width": 1920
}
}
},
{
"key": "photo_image_full_size_original",
"value": {
"image_value": {
"height": 1080,
"url": "https://pbs.twimg.com/card_img/2069527208830345216/znw4vBjI?format=jpg&name=orig",
"width": 1920
}
}
},
{
"key": "vanity_url",
"value": {
"scribe_key": "vanity_url",
"string_value": "developer.nvidia.com"
}
},
{
"key": "photo_image_full_size",
"value": {
"image_value": {
"height": 314,
"url": "https://pbs.twimg.com/card_img/2069527208830345216/znw4vBjI?format=jpg&name=600x314",
"width": 600
}
}
},
{
"key": "thumbnail_image_color",
"value": {
"image_color_value": {
"palette": [
{
"percentage": 95.13,
"rgb": {
"blue": 0,
"green": 0,
"red": 0
}
},
{
"percentage": 1.53,
"rgb": {
"blue": 196,
"green": 196,
"red": 196
}
},
{
"percentage": 0.64,
"rgb": {
"blue": 222,
"green": 237,
"red": 0
}
},
{
"percentage": 0.54,
"rgb": {
"blue": 1,
"green": 75,
"red": 48
}
},
{
"percentage": 0.5,
"rgb": {
"blue": 1,
"green": 135,
"red": 86
}
}
]
}
}
},
{
"key": "title",
"value": {
"string_value": "Run Step 3.7 Flash on NVIDIA GPUs with Enterprise-Ready Multimodal AI | NVIDIA Technical Blog"
}
},
{
"key": "summary_photo_image_color",
"value": {
"image_color_value": {
"palette": [
{
"percentage": 95.13,
"rgb": {
"blue": 0,
"green": 0,
"red": 0
}
},
{
"percentage": 1.53,
"rgb": {
"blue": 196,
"green": 196,
"red": 196
}
},
{
"percentage": 0.64,
"rgb": {
"blue": 222,
"green": 237,
"red": 0
}
},
{
"percentage": 0.54,
"rgb": {
"blue": 1,
"green": 75,
"red": 48
}
},
{
"percentage": 0.5,
"rgb": {
"blue": 1,
"green": 135,
"red": 86
}
}
]
}
}
},
{
"key": "summary_photo_image_x_large",
"value": {
"image_value": {
"height": 1080,
"url": "https://pbs.twimg.com/card_img/2069527208830345216/znw4vBjI?format=png&name=2048x2048_2_exp",
"width": 1920
}
}
},
{
"key": "summary_photo_image",
"value": {
"image_value": {
"height": 314,
"url": "https://pbs.twimg.com/card_img/2069527208830345216/znw4vBjI?format=jpg&name=600x314",
"width": 600
}
}
},
{
"key": "photo_image_full_size_color",
"value": {
"image_color_value": {
"palette": [
{
"percentage": 95.13,
"rgb": {
"blue": 0,
"green": 0,
"red": 0
}
},
{
"percentage": 1.53,
"rgb": {
"blue": 196,
"green": 196,
"red": 196
}
},
{
"percentage": 0.64,
"rgb": {
"blue": 222,
"green": 237,
"red": 0
}
},
{
"percentage": 0.54,
"rgb": {
"blue": 1,
"green": 75,
"red": 48
}
},
{
"percentage": 0.5,
"rgb": {
"blue": 1,
"green": 135,
"red": 86
}
}
]
}
}
},
{
"key": "photo_image_full_size_x_large",
"value": {
"image_value": {
"height": 1080,
"url": "https://pbs.twimg.com/card_img/2069527208830345216/znw4vBjI?format=png&name=2048x2048_2_exp",
"width": 1920
}
}
},
{
"key": "card_url",
"value": {
"scribe_key": "card_url",
"string_value": "https://t.co/A6VftfrYyK"
}
},
{
"key": "summary_photo_image_original",
"value": {
"image_value": {
"height": 1080,
"url": "https://pbs.twimg.com/card_img/2069527208830345216/znw4vBjI?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/A6VftfrYyK",
"user_refs_results": []
},
"place": {},
"entities": {
"hashtags": [],
"symbols": [],
"urls": [
{
"display_url": "developer.nvidia.com/blog/run-step-…",
"expanded_url": "https://developer.nvidia.com/blog/run-step-3-7-flash-on-nvidia-gpus-with-enterprise-ready-multimodal-ai/",
"indices": [
333,
356
],
"url": "https://t.co/A6VftfrYyK"
}
],
"user_mentions": []
},
"quoted_tweet": null,
"retweeted_tweet": null,
"isLimitedReply": false,
"communityInfo": null,
"article": null
}