Viewing enriched Twitter post
Improve latency up to 1.68x with NVFP4 and MXFP8 using Diffusers and TorchAO on Blackwell across a suite of different models 🔥. Squeeze out maximum performance with recipes involving selective quantization and regional compilation. 🔗 Read our latest blog from @vkuzo (@Meta) and @RisingSayak (@HuggingFace): https://t.co/QRHwAiOSc5 #PyTorch #TorchAO #MXFP8 #NVFP4 #OpenSourceAI
{
"media": [
{
"type": "photo",
"url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2041923082353320443/media_0.jpg",
"filename": "media_0.jpg"
}
],
"processed_at": "2026-04-08T17:09:03.875277",
"pipeline_version": "2.0"
}{
"type": "tweet",
"id": "2041923082353320443",
"url": "https://x.com/PyTorch/status/2041923082353320443",
"twitterUrl": "https://twitter.com/PyTorch/status/2041923082353320443",
"text": "Improve latency up to 1.68x with NVFP4 and MXFP8 using Diffusers and TorchAO on Blackwell across a suite of different models 🔥. \n\nSqueeze out maximum performance with recipes involving selective quantization and regional compilation.\n\n🔗 Read our latest blog from @vkuzo (@Meta) and @RisingSayak (@HuggingFace): https://t.co/QRHwAiOSc5\n\n#PyTorch #TorchAO #MXFP8 #NVFP4 #OpenSourceAI",
"source": "Twitter for iPhone",
"retweetCount": 0,
"replyCount": 0,
"likeCount": 3,
"quoteCount": 0,
"viewCount": 714,
"createdAt": "Wed Apr 08 16:56:14 +0000 2026",
"lang": "en",
"bookmarkCount": 3,
"isReply": false,
"inReplyToId": null,
"conversationId": "2041923082353320443",
"displayTextRange": [
0,
277
],
"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": 483929,
"following": 83,
"status": "",
"canDm": false,
"canMediaTag": true,
"createdAt": "Fri Sep 16 00:56:26 +0000 2016",
"entities": {
"description": {
"urls": []
},
"url": {}
},
"fastFollowersCount": 0,
"favouritesCount": 872,
"hasCustomTimelines": true,
"isTranslator": false,
"mediaCount": 1422,
"statusesCount": 3186,
"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"
}
],
"symbols": [],
"urls": [],
"user_mentions": []
},
"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/vb2nFWk8xz",
"expanded_url": "https://twitter.com/PyTorch/status/2041923082353320443/photo/1",
"ext_media_availability": {
"status": "Available"
},
"features": {
"large": {
"faces": []
},
"orig": {
"faces": []
}
},
"id_str": "2041923061348249600",
"indices": [
278,
301
],
"media_key": "3_2041923061348249600",
"media_results": {
"id": "QXBpTWVkaWFSZXN1bHRzOgwAAQoAARxWXjSqVzAACgACHFZeOY5XIfsAAA==",
"result": {
"__typename": "ApiMedia",
"id": "QXBpTWVkaWE6DAABCgABHFZeNKpXMAAKAAIcVl45jlch+wAA",
"media_key": "3_2041923061348249600"
}
},
"media_url_https": "https://pbs.twimg.com/media/HFZeNKpXMAAjGYM.jpg",
"original_info": {
"focus_rects": [
{
"h": 1075,
"w": 1920,
"x": 0,
"y": 0
},
{
"h": 1080,
"w": 1080,
"x": 564,
"y": 0
},
{
"h": 1080,
"w": 947,
"x": 631,
"y": 0
},
{
"h": 1080,
"w": 540,
"x": 834,
"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/vb2nFWk8xz"
}
]
},
"card": null,
"place": {},
"entities": {
"hashtags": [
{
"indices": [
336,
344
],
"text": "PyTorch"
},
{
"indices": [
345,
353
],
"text": "TorchAO"
},
{
"indices": [
354,
360
],
"text": "MXFP8"
},
{
"indices": [
361,
367
],
"text": "NVFP4"
},
{
"indices": [
368,
381
],
"text": "OpenSourceAI"
}
],
"symbols": [],
"urls": [
{
"display_url": "pytorch.org/blog/faster-di…",
"expanded_url": "https://pytorch.org/blog/faster-diffusion-on-blackwell-mxfp8-and-nvfp4-with-diffusers-and-torchao/",
"indices": [
311,
334
],
"url": "https://t.co/QRHwAiOSc5"
}
],
"user_mentions": [
{
"id_str": "438924950",
"indices": [
263,
269
],
"name": "Vasiliy Kuznetsov",
"screen_name": "vkuzo"
},
{
"id_str": "2425151",
"indices": [
271,
276
],
"name": "Meta",
"screen_name": "Meta"
},
{
"id_str": "593407733",
"indices": [
282,
294
],
"name": "Sayak Paul",
"screen_name": "RisingSayak"
},
{
"id_str": "778764142412984320",
"indices": [
296,
308
],
"name": "Hugging Face",
"screen_name": "HuggingFace"
}
]
},
"quoted_tweet": null,
"retweeted_tweet": null,
"isLimitedReply": false,
"communityInfo": null,
"article": null
}