Nvidia has denied reports that it plans to launch a China-specific language processing unit by the end of the year, saying no such product is currently on its roadmap.
The denial followed a report claiming Nvidia was preparing limited shipments of an AI processor tailored for Chinese customers and that some buyers had already placed orders.
The reported chip was described as a version of Nvidia’s LPU technology, based on intellectual property licensed from startup Groq, and designed to work alongside GPUs to accelerate AI inference and chatbot responses.
Nvidia said it currently has no LPU sales in China and no China-specific version planned.
The clarification comes as Nvidia continues to navigate U.S. export restrictions affecting advanced AI chip sales to China. Washington has allowed limited shipments of some products, including H200 processors to selected Chinese companies, while other next-generation systems remain restricted.
Nvidia has also been promoting alternative products such as its Vera CPU in China as domestic rivals including Huawei gain ground in the AI semiconductor market.
