[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-nvidia-denies-building-a-china-specific-lpu-chip":10,"sections":41},{"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":30,"tags":31,"sources":36,"feedback":40,"feedback_at":22,"cost_usd":40,"total_tokens":40},5779,"nvidia-denies-building-a-china-specific-lpu-chip","Nvidia Denies Building a China Specific LPU Chip","Nvidia says reports of a China specific LPU chip are wrong, but its narrow denial leaves room for standard LPU sales to Chinese buyers.","Nvidia says a report claiming it will ship a China-specific AI chip by year's end is simply wrong.\n\nThe Information reported that Nvidia planned small-batch shipments of a language processing unit, or LPU, built for Chinese customers by the end of 2026, with orders already placed. Citing two Nvidia employees, the outlet said the chip was a variant of the LPU decode accelerator Nvidia unveiled at GTC in March, changed only in software so it can pair with processors already sold in China. Nvidia rejected the story outright. \"The reporting in The Information on NVIDIA's LPU is incorrect. We have no LPU sales in the China market today, and no China-specific LPU product in our roadmap,\" a company spokesperson told Tom's Hardware.\n\nThe denial is narrower than it looks. It covers current sales and a China-specific product, but says nothing about whether the standard LPU - built on Samsung's 4nm process with 512MB of SRAM per die and no HBM, due to ship in Q3 2026 to customers like OpenAI - could reach China unmodified. That gap matters because a SRAM-only decode chip with no HBM stack may already clear U.S. export thresholds without a cut-down SKU, which is exactly the workaround The Information's sources described.\n\nThis is the second time this year Nvidia has had to knock down a China-LPU story - Jensen Huang called a similar report in March \"totally false\" - and it lands the same week ByteDance and Tencent each took delivery of roughly 10,000 H200 GPUs, the first real Nvidia chip volume to reach mainland China since December's U.S. approval.","[\"nvidia\",\"china\",\"ai-chips\",\"export-controls\"]","2026-08-21T11:39:39.000Z","2026-08-21T12:22:09.596Z","2026-08-21T12:22:21.620Z","published",null,[24],{"id":25,"reviewer":26,"round":27,"reason":28,"status":29},"publisher-r1","publisher",1,"The body describes the chip as \"the Groq 3 LPU Nvidia unveiled at GTC\" — Groq is a separate, competing chip company, so attributing a Groq-named product to Nvidia is an internal factual inconsistency that needs correction before publishing.","resolved","hardware",[32,33,34,35],"nvidia","china","ai-chips","export-controls",[37],{"name":38,"url":39},"Tom's Hardware","https:\u002F\u002Fwww.tomshardware.com\u002Ftech-industry\u002Fsemiconductors\u002Fnvidia-denies-report-it-will-ship-groq-based-lpus-to-china-by-year-end",0,{"sections":42},[43,48,53,58,63,67,72,77,82,87,92,97,102,107],{"name":44,"slug":45,"count":46,"latest_published_at":47},"AI","ai",3301,"2026-08-21T12:17:31.000Z",{"name":49,"slug":50,"count":51,"latest_published_at":52},"Security","security",451,"2026-08-21T13:35:23.000Z",{"name":54,"slug":55,"count":56,"latest_published_at":57},"Policy","policy",212,"2026-08-21T12:20:54.000Z",{"name":59,"slug":60,"count":61,"latest_published_at":62},"Deals","deals",179,"2026-06-29T20:02:07.000Z",{"name":64,"slug":30,"count":65,"latest_published_at":66},"Hardware",143,"2026-08-21T11:40:00.000Z",{"name":68,"slug":69,"count":70,"latest_published_at":71},"Consumer Tech","consumer-tech",95,"2026-08-18T16:05:00.000Z",{"name":73,"slug":74,"count":75,"latest_published_at":76},"Science","science",91,"2026-08-20T10:01:48.000Z",{"name":78,"slug":79,"count":80,"latest_published_at":81},"Software","software",73,"2026-08-18T07:51:50.000Z",{"name":83,"slug":84,"count":85,"latest_published_at":86},"Dev Tools","dev-tools",69,"2026-08-18T04:00:00.000Z",{"name":88,"slug":89,"count":90,"latest_published_at":91},"Startups","startups",48,"2026-08-20T18:34:26.000Z",{"name":93,"slug":94,"count":95,"latest_published_at":96},"Gaming","gaming",41,"2026-07-09T04:00:00.000Z",{"name":98,"slug":99,"count":100,"latest_published_at":101},"General","general",33,"2026-08-18T22:18:13.000Z",{"name":103,"slug":104,"count":105,"latest_published_at":106},"Reviews","reviews",20,"2026-06-24T12:00:01.000Z",{"name":108,"slug":109,"count":110,"latest_published_at":111},"How-To","how-to",6,"2026-06-16T09:00:00.000Z"]