[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-a-chip-that-lets-ai-weights-mix-precision-block-by-block":10,"sections":34},{"siteName":4,"siteTagline":5,"publisherName":4,"contactEmail":6},"The Revision","Tech news, decoded.","editor@therevision.news",{"gaMeasurementId":8,"adsenseClientId":9},"G-ZW2MV82GYR","ca-pub-8533917693782264",{"article":11},{"id":12,"slug":13,"title":14,"dek":15,"body_md":16,"tags_json":17,"published_at":18,"created_at":19,"updated_at":20,"status":21,"review_note":22,"review_notes":23,"image_url":22,"persona_id":22,"persona_name":22,"section":24,"tags":25,"sources":29,"feedback":33,"feedback_at":22,"cost_usd":33,"total_tokens":33},9602,"a-chip-that-lets-ai-weights-mix-precision-block-by-block","A Chip That Lets AI Weights Mix Precision Block by Block","A new transformer chip assigns different bit-widths to blocks within a single weight matrix, cutting AI inference costs without gutting accuracy.","A chip that lets AI models mix bit-widths within a single weight matrix, not just across layers, has made it out of the lab.\n\nThe project, called ShatterQuant, pairs a quantization method with custom accelerator hardware. Instead of assigning one bit-width to an entire tensor, it splits weights into blocks and gives each block 1, 2, 4, or 8 bits based on how sensitive that block is to precision loss. The matching chip, built on TSMC's 16nm process and running at 1 GHz, reconfigures its processing elements to match each block's precision and handles softmax and other nonlinear math on-chip. In testing, it hit 1.5 TOPS of throughput, 760 GOPS per square millimeter of area, and 2.8 TOPS per watt.\n\nOn image classification with DeiT on ImageNet-1K, the approach landed within 3.3% of the accuracy of leading mixed-precision methods while using, on average, 2 fewer bits per weight - a real efficiency gain. It also held up on PixelDiT, an image-generation model, without a visible quality hit. That is the entire pitch of mixed-precision quantization: squeeze out memory and power without falling off an accuracy cliff.\n\nWorth remembering: this is a 16nm research chip, not a product roadmap. Commercial AI accelerators have been creeping toward finer-grained precision control for years. The open question is whether fine-grained, intra-tensor quantization like this ever makes it into shipping silicon, or stays a clever idea that dies in a PDK.","[\"quantization\",\"ai-hardware\",\"semiconductors\"]","2026-10-02T04:00:00.000Z","2026-10-03T02:29:32.041Z","2026-10-03T02:29:37.826Z","published",null,[],"hardware",[26,27,28],"quantization","ai-hardware","semiconductors",[30],{"name":31,"url":32},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2610.00207",0,{"sections":35},[36,40,44,48,53,56,60,65,70,75,80,85,90,95],{"name":37,"slug":38,"count":39,"latest_published_at":18},"AI","ai",5896,{"name":41,"slug":42,"count":43,"latest_published_at":18},"Security","security",837,{"name":45,"slug":46,"count":47,"latest_published_at":18},"Policy","policy",438,{"name":49,"slug":50,"count":51,"latest_published_at":52},"Deals","deals",317,"2026-10-01T22:00:00.000Z",{"name":54,"slug":24,"count":55,"latest_published_at":18},"Hardware",199,{"name":57,"slug":58,"count":59,"latest_published_at":18},"Science","science",171,{"name":61,"slug":62,"count":63,"latest_published_at":64},"Consumer Tech","consumer-tech",155,"2026-10-01T19:54:10.000Z",{"name":66,"slug":67,"count":68,"latest_published_at":69},"Dev Tools","dev-tools",96,"2026-10-01T16:57:03.000Z",{"name":71,"slug":72,"count":73,"latest_published_at":74},"Software","software",93,"2026-09-30T21:41:11.000Z",{"name":76,"slug":77,"count":78,"latest_published_at":79},"Startups","startups",90,"2026-10-01T21:55:22.000Z",{"name":81,"slug":82,"count":83,"latest_published_at":84},"Gaming","gaming",53,"2026-10-02T02:50:39.000Z",{"name":86,"slug":87,"count":88,"latest_published_at":89},"General","general",50,"2026-09-30T21:37:54.000Z",{"name":91,"slug":92,"count":93,"latest_published_at":94},"Reviews","reviews",31,"2026-09-28T14:31:34.000Z",{"name":96,"slug":97,"count":98,"latest_published_at":99},"How-To","how-to",7,"2026-10-01T09:00:00.000Z"]