🐦 Twitter Post Details

Viewing enriched Twitter post

@PyTorch

Helion's autotuner has been a powerful tool for optimizing ML kernels, but it came with a challenge: long autotuning sessions that could take 10+ minutes, sometimes even hours. The PyTorch team at Meta set out to solve this bottleneck using machine learning itself 🖇️ Read here how they did it: https://t.co/N8lYGeXuv9 Spoiler alert: Using Likelihood-Free Bayesian Optimization Pattern Search, they achieved a 36.5% reduction in autotuning time for NVIDIA B200 kernels while improving kernel latency by 2.6%. For AMD MI350 kernels, they saw a 25.9% time reduction with 1.7% better latency. Some kernels showed even more dramatic improvements—up to 50% faster autotuning and >15% latency gains. ✍️ Ethan Che, Oguz Ulgen, Maximilian Balandat, Jongsok Choi, Jason Ansel (Meta) #PyTorch #Helion #MachineLearning #BayesianOptimization #OpenSourceAI #Performance

Media 1
View on Twitter

📊 Media Metadata

{
  "media": [
    {
      "type": "photo",
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2026356689230840137/media_0.jpg?",
      "filename": "media_0.jpg"
    }
  ],
  "processed_at": "2026-03-01T19:40:04.432301",
  "pipeline_version": "2.0"
}

🔧 Raw API Response

{
  "type": "tweet",
  "id": "2026356689230840137",
  "url": "https://x.com/PyTorch/status/2026356689230840137",
  "twitterUrl": "https://twitter.com/PyTorch/status/2026356689230840137",
  "text": "Helion's autotuner has been a powerful tool for optimizing ML kernels, but it came with a challenge: long autotuning sessions that could take 10+ minutes, sometimes even hours. The PyTorch team at Meta set out to solve this bottleneck using machine learning itself\n\n🖇️ Read here how they did it: https://t.co/N8lYGeXuv9\n\nSpoiler alert: Using Likelihood-Free Bayesian Optimization Pattern Search, they achieved a 36.5% reduction in autotuning time for NVIDIA B200 kernels while improving kernel latency by 2.6%. For AMD MI350 kernels, they saw a 25.9% time reduction with 1.7% better latency. Some kernels showed even more dramatic improvements—up to 50% faster autotuning and >15% latency gains.\n\n✍️ Ethan Che, Oguz Ulgen, Maximilian Balandat, Jongsok Choi, Jason Ansel (Meta)\n\n#PyTorch #Helion #MachineLearning #BayesianOptimization #OpenSourceAI #Performance",
  "source": "Twitter for iPhone",
  "retweetCount": 4,
  "replyCount": 4,
  "likeCount": 73,
  "quoteCount": 2,
  "viewCount": 8461,
  "createdAt": "Tue Feb 24 18:00:57 +0000 2026",
  "lang": "en",
  "bookmarkCount": 40,
  "isReply": false,
  "inReplyToId": null,
  "conversationId": "2026356689230840137",
  "displayTextRange": [
    0,
    278
  ],
  "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": 476861,
    "following": 81,
    "status": "",
    "canDm": false,
    "canMediaTag": true,
    "createdAt": "Fri Sep 16 00:56:26 +0000 2016",
    "entities": {
      "description": {
        "urls": []
      },
      "url": {}
    },
    "fastFollowersCount": 0,
    "favouritesCount": 837,
    "hasCustomTimelines": true,
    "isTranslator": false,
    "mediaCount": 1328,
    "statusesCount": 3065,
    "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/JUfLgC5YxJ",
        "expanded_url": "https://twitter.com/PyTorch/status/2026356689230840137/photo/1",
        "ext_media_availability": {
          "status": "Available"
        },
        "features": {
          "large": {
            "faces": [
              {
                "h": 71,
                "w": 71,
                "x": 585,
                "y": 513
              }
            ]
          },
          "orig": {
            "faces": [
              {
                "h": 71,
                "w": 71,
                "x": 585,
                "y": 513
              }
            ]
          }
        },
        "id_str": "2026356668540370944",
        "indices": [
          279,
          302
        ],
        "media_key": "3_2026356668540370944",
        "media_results": {
          "id": "QXBpTWVkaWFSZXN1bHRzOgwAAQoAARwfEKdol8AACgACHB8QrDnXQUkAAA==",
          "result": {
            "__typename": "ApiMedia",
            "id": "QXBpTWVkaWE6DAABCgABHB8Qp2iXwAAKAAIcHxCsOddBSQAA",
            "media_key": "3_2026356668540370944"
          }
        },
        "media_url_https": "https://pbs.twimg.com/media/HB8Qp2iXwAANTkR.jpg",
        "original_info": {
          "focus_rects": [
            {
              "h": 1075,
              "w": 1920,
              "x": 0,
              "y": 5
            },
            {
              "h": 1080,
              "w": 1080,
              "x": 840,
              "y": 0
            },
            {
              "h": 1080,
              "w": 947,
              "x": 973,
              "y": 0
            },
            {
              "h": 1080,
              "w": 540,
              "x": 1218,
              "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/JUfLgC5YxJ"
      }
    ]
  },
  "card": null,
  "place": {},
  "entities": {
    "hashtags": [
      {
        "indices": [
          778,
          786
        ],
        "text": "PyTorch"
      },
      {
        "indices": [
          787,
          794
        ],
        "text": "Helion"
      },
      {
        "indices": [
          795,
          811
        ],
        "text": "MachineLearning"
      },
      {
        "indices": [
          812,
          833
        ],
        "text": "BayesianOptimization"
      },
      {
        "indices": [
          834,
          847
        ],
        "text": "OpenSourceAI"
      },
      {
        "indices": [
          848,
          860
        ],
        "text": "Performance"
      }
    ],
    "symbols": [],
    "urls": [
      {
        "display_url": "hubs.la/Q044kN5G0",
        "expanded_url": "https://hubs.la/Q044kN5G0",
        "indices": [
          296,
          319
        ],
        "url": "https://t.co/N8lYGeXuv9"
      }
    ],
    "user_mentions": []
  },
  "quoted_tweet": null,
  "retweeted_tweet": null,
  "isLimitedReply": false,
  "article": null
}