Nvidia has denied a report by The Information claiming it plans to ship a China-specific language processing unit (LPU) using licensed Groq technology by the end of 2026. While U.S. export controls and Beijing's regulatory hurdles have severely restricted Nvidia's access to the Chinese market, the region faces a critical AI computing shortage. Nvidia CEO Jensen Huang previously conceded that the company has largely lost ground to domestic rival Huawei Technologies, which is launching its own Ascend 950DT chip.
Nvidia LPU report denial
- ▪The Information reported on August 20, 2026, citing two Nvidia employees, that Nvidia planned to begin small-batch shipments of an artificial-intelligence chip designed for Chinese customers by the end of 2026.
- ▪Nvidia on August 20, 2026 denied a report by The Information claiming that the company plans to begin shipping a language processing unit tailored for Chinese customers by the end of 2026.
- ▪An Nvidia spokesperson stated on August 20, 2026 that the company has no language processing unit sales in the China market today and no China-specific language processing unit product on its roadmap.
Groq technology licensing
- ▪The Information reported that the rumored Nvidia chip was a version of Nvidia's language processing unit developed using technology licensed from startup Groq to speed up AI chatbot responses.
- ▪The Groq 3 language processing unit is built on Samsung's 4nm process with 512MB of SRAM per die and no HBM, and was scheduled to ship in Q3 2026 to customers including OpenAI.
US export control compliance
- ▪The Information reported that Nvidia modified software to allow its language processing unit to operate with processors available in China after its next-generation Vera Rubin AI system became unavailable due to U.S. restrictions.
- ▪U.S. export thresholds for China are set on compute density and bandwidth, allowing an SRAM-only decode accelerator with no HBM stack to be exported without a cut-down SKU.
China market access restrictions
- ▪ByteDance and Tencent each recently took delivery of approximately 10,000 Nvidia H200 chips, representing the first meaningful Nvidia accelerator volume to enter mainland China since December 2025.
- ▪Chinese officials blocked purchases of Nvidia's H20 chip in 2025 and only recently permitted some H200 imports, meaning U.S. compliance alone does not guarantee delivery in China.
- ▪The United States in May 2026 approved sales of Nvidia's H200 AI chips to a limited group of Chinese firms, including Alibaba, Tencent, and ByteDance.
China AI chip shortage
- ▪China's largest technology companies are working to expand domestic chip production through 2027, creating a critical window for Nvidia to re-engage Chinese customers.
- ▪Chinese AI companies face severe computing bottlenecks, which led Moonshot AI to freeze new sign-ups and DeepSeek to raise developer fees.
Huawei competitive pressure
- ▪Huawei Technologies is preparing to release its Ascend 950DT chip, optimized for decode and training, in Q4 2026 to compete directly in the Chinese AI hardware market.
- ▪Nvidia Chief Executive Jensen Huang stated in May 2026 that Nvidia had largely conceded China's AI chip market to Huawei Technologies.
Story comments
Loading comments…