Breaking News
Nvidia on Thursday denied that it plans to begin shipping a language processing unit tailored for Chinese customers by year-end, saying it has no China-specific version of the product on its roadmap.
"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," an Nvidia spokesperson said.
The Information had reported earlier Thursday, citing two Nvidia employees, that the company planned to begin small-batch shipments of an AI chip designed for Chinese customers by the end of the year, and that several customers had already placed orders. According to that report, the chip was a version of Nvidia's LPU, a processor developed using technology licensed from startup Groq that works alongside GPUs to speed up AI chatbot responses.
The said chip complied with U.S. export-control rules and that Nvidia had modified software to let the LPU operate with processors available in China, after the company's next-generation Vera Rubin AI system became unavailable in the Chinese market because of U.S. restrictions, according to the report.
LPUs are a class of chip optimized specifically for running inference on large language models, distinct from the general-purpose GPUs that make up the bulk of Nvidia's business and that remain central to AI training workloads. Groq, the startup whose technology reportedly underpins the disputed chip, has positioned its own LPU architecture as a faster, more power-efficient alternative to GPU-based inference for chatbot and reasoning applications, a niche that has drawn increasing attention as AI companies shift spending from training toward serving live user queries at scale.
Nvidia's China business has been in flux in recent months, shaped largely by shifting U.S. export policy. Washington approved sales of Nvidia's H200 AI chips to a limited group of Chinese firms, including Alibaba, Tencent and ByteDance, in May, though deliveries only recently began after months of regulatory back-and-forth. Nvidia has also been marketing its Vera CPU to Chinese customers, part of a broader effort to retain a foothold in the market as its most advanced AI accelerators remain restricted from sale there under current export controls.
"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," an Nvidia spokesperson said.
The Information had reported earlier Thursday, citing two Nvidia employees, that the company planned to begin small-batch shipments of an AI chip designed for Chinese customers by the end of the year, and that several customers had already placed orders. According to that report, the chip was a version of Nvidia's LPU, a processor developed using technology licensed from startup Groq that works alongside GPUs to speed up AI chatbot responses.
The said chip complied with U.S. export-control rules and that Nvidia had modified software to let the LPU operate with processors available in China, after the company's next-generation Vera Rubin AI system became unavailable in the Chinese market because of U.S. restrictions, according to the report.
LPUs are a class of chip optimized specifically for running inference on large language models, distinct from the general-purpose GPUs that make up the bulk of Nvidia's business and that remain central to AI training workloads. Groq, the startup whose technology reportedly underpins the disputed chip, has positioned its own LPU architecture as a faster, more power-efficient alternative to GPU-based inference for chatbot and reasoning applications, a niche that has drawn increasing attention as AI companies shift spending from training toward serving live user queries at scale.
Nvidia's China business has been in flux in recent months, shaped largely by shifting U.S. export policy. Washington approved sales of Nvidia's H200 AI chips to a limited group of Chinese firms, including Alibaba, Tencent and ByteDance, in May, though deliveries only recently began after months of regulatory back-and-forth. Nvidia has also been marketing its Vera CPU to Chinese customers, part of a broader effort to retain a foothold in the market as its most advanced AI accelerators remain restricted from sale there under current export controls.
See What’s Next in Tech With the Fast Forward Newsletter
Tweets From @varindiamag
Nothing to see here - yet
When they Tweet, their Tweets will show up here.
