Huawei moves up Ascend 960DT AI chip launch to Q1 2027

Huawei is moving up the launch of its next-generation Ascend 960DT AI chip to the first quarter of 2027, as the Chinese tech giant races to challenge Nvidia, the company said Thursday at its Huawei Connect conference. Huawei had previously planned to launch the chip in the third quarter of 2027, a company spokesperson told TechCrunch, adding that Ascend 960-series chips are shipping ahead of schedule, with performance doubling year by year. David Wang, Huawei’s rotating and acting chairman, announced the updated timeline at the conference. The announcement comes just a week before US President Trump and Chinese President Xi Jinping are set to meet on September 24 in Washington, DC.

Huawei is trying to turn hundreds of thousands, and eventually millions, of AI chips into one giant computer, an approach it calls its Peerium Computing Architecture. The approach relies on UnifiedBus, Huawei’s technology for linking processors with memory, storage, and networking hardware. Rotating chairman Eric Xu said in a company statement that Huawei is using the new architecture to build larger AI computing systems designed for both training and inference. The company’s Atlas 950 SuperPoD and SuperCluster are the first systems based on the architecture, and Huawei says an Atlas 950 SuperCluster can connect up to 256,000 accelerator cards.

The accelerated chip timeline raises questions about Huawei’s broader AI systems, however. China tech analyst Rui Ma noted on X that Huawei had previously said its Atlas 960 SuperPoD would scale to 15,488 Ascend 960 chips, while this week’s announcement referred to a system with 4,096 chips. “The chip itself is coming WAY earlier, but the SuperPoD they announced is much smaller than what they originally laid out,” Ma wrote.

Huawei has continued to advance its chip ambitions despite US restrictions on China’s access to advanced semiconductor technology. Ma said those restrictions are unlikely to stop China from pursuing its own semiconductor development, arguing the stakes for self-sufficiency are now too high for the effort to be derailed. Trump has pushed back against calls from AI industry leaders to slow AI development over safety concerns, arguing the US needs to maintain its lead over China, while Xu has argued China needs to accelerate its own AI development to catch up with the US — saying, according to the Financial Times, that Chinese companies need to advance further before they can fully understand and address the risks posed by more powerful AI systems.

Why it matters

Huawei’s willingness to ship a smaller system sooner rather than a larger one on the original schedule suggests speed to market, not just scale, is now the priority in China’s race to close the AI-chip gap with Nvidia — right as Washington and Beijing head into a high-stakes summit.