Huawei to Test New Ascend 910D Chip Amid NVIDIA Crisis

2 hours ago 1
  • Published on April 28, 2025
  • In AI News

Huawei seeks to replace some of NVIDIA’s high-end processors, promoting self-sufficiency.

Huawei is preparing to test its new AI chip, the Ascend 910D, in China by reaching out to various tech companies, The Wall Street Journal reported. The move comes as Huawei seeks to replace some of NVIDIA’s high-end processors following Washington’s tightening of semiconductor export restrictions to China.

The Llama Club Article Foot

The Ascend 910D is set for initial sample delivery by late May, and Huawei has already approached several Chinese tech companies to assess the chip’s technical feasibility. The tests will determine if the new chip can match or outperform NVIDIA’s H100, a key processor for AI development. 

Huawei’s efforts underline Beijing’s push for a self-sufficient semiconductor industry. This comes shortly after reports claiming that Huawei is preparing to ship its Ascend 910C AI chips amid US restrictions.

The company’s chip development remains in its early stages and will require a series of technical evaluations before it can be deployed to customers. The new chip is part of Huawei’s broader strategy to fortify China’s AI and semiconductor industries after being placed on a US trade blacklist nearly six years ago. 

The company has already shipped more than 8,00,000 units of its Ascend 910B and 910C chips to clients this year. This includes state-owned telecommunications carriers and private AI developers such as ByteDance, the Chinese tech company that owns TikTok.

Washington’s recent move to restrict sales of NVIDIA’s H20 chip has created opportunities for domestic competitors. NVIDIA also announced in an exchange filing that the US government has potentially charged it $5.5 billion for exporting H20 AI chips to China, one of its key markets, without a license.

Despite manufacturing difficulties, Chinese firms, including Huawei, have been able to develop AI chips comparable to those of NVIDIA, although there is a performance lag of several years. 

Facing challenges such as limited access to TSMC and restricted availability of high-end components, Huawei has shifted its focus toward building systems that connect multiple chips.

Picture of Sanjana Gupta

Sanjana Gupta

An information designer who loves to learn about and try new developments in the field of tech and AI. She likes to spend her spare time reading and exploring absurdism in literature.

Related Posts

Develop AI driven team

Association of Data Scientists

GenAI Corporate Training Programs

Our Upcoming Conference

India's Biggest conference on Data Engineering

MAY. 15-16 2025 | 📍 Hotel Radisson Blu, Bengaluru

Download the easiest way to
stay informed

Subscribe to The Belamy: Our Weekly Newsletter

Biggest AI stories, delivered to your inbox every week.

Data Engineering Summit 2025

May 15 - 16, 2025 | 📍 Hotel Radisson Blu, Bengaluru

MachineCon GCC Summit 2025

June 20 to 22, 2025 | 📍 ITC Grand, Goa

Cypher India 2025

Sep 17 to 19, 2025 | 📍KTPO, Whitefield, Bengaluru, India

MLDS 2026

India's Biggest Developers Summit | 📍Nimhans Convention Center, Bengaluru

Rising 2026

India's Biggest Summit on Women in Tech & AI 📍 Bengaluru

Happy Llama 2025

AI Startups Conference.April 25, 2025 | 📍 Hotel Radisson Blu, Bengaluru, India

Read Entire Article