Observed Signal · Sep 21, 2026 · Technical Release · Source: Trending Topics (DACH/CEE Innovation & Tech) · Impact: 4/5 · Sentiment: Neutral
Infrastructure Market: Huawei Unveils Ascend 960 Chips, Claims System-Level Parity with Nvidia
At Huawei Connect in Shanghai, Huawei unveiled its next-generation AI accelerators—the Ascend 960DT and 960PR—scheduled for Q1 and Q3 2027, respectively, about three quarters earlier than planned. Designed for training and inference of advanced open-weight models, these chips power the Atlas 960E SuperPoD, a system connecting 4,096 processors with 8 EFLOPS FP8 and up to 1 PB of high-speed memory. Huawei emphasizes system-level integration and open-source ecosystems, with over 40 models pre-trained on Ascend, including GLM-5. However, per-chip performance still trails Nvidia's Rubin generation, though system-level parity is closer. DeepSeek has ordered at least 160,000 Ascend 950DT chips for inference but still trains on Nvidia hardware. Huawei's in-house HBM development addresses US export restrictions, and the company projects a 100,000-fold increase in AI token processing by 2035.
Major AI infrastructure release from a significant global player, impacting the AI hardware market and potentially influencing adtech's AI adoption.
Key Takeaways & Evidence Grounding
- Huawei will release Ascend 960DT in Q1 2027 and Ascend 960PR in Q3 2027, three quarters earlier than planned.
- The Atlas 960E SuperPoD connects 4,096 AI processors, delivering 8 EFLOPS FP8 and up to 1 PB of high-speed memory.
- DeepSeek has ordered at least 160,000 Ascend 950DT chips for inference but still trains on Nvidia hardware.
- Over 40 AI models, including Zhipu AI's GLM-5, have been trained natively on Ascend hardware.
- Huawei expects AI token processing to increase 100,000-fold by 2035, and the Ascend 960PR achieves 8 PFLOPS FP4, double the originally planned performance.
Connected Companies & Entities
4 Entities mappedHuawei
Diversified technology group spanning devices, cloud, app distribution and advertising.
“Huawei announced new Ascend chips and Atlas 960E SuperPod at Huawei Connect....”
NVIDIA
Accelerated computing company spanning AI software, cloud and gaming.
“Nvidia's Rubin generation is used as the comparison for Huawei's new chips....”
DeepSeek
LLM developer offering AI chat and API access.
“DeepSeek has ordered at least 160,000 Ascend chips and uses Huawei's inference stack....”
Z.ai (also marketed as Zhipu AI / 智谱AI)
Chinese LLM developer selling APIs, AI agents and MaaS.
“Zhipu AI trained its GLM-5 model solely on Huawei Ascend chips....”
Ontology Mapping & Concepts
Track Real-Time Market Signals & Shifts
Set up custom watchlists to receive automated, evidence-grounded executive digests whenever material signals or shifts occur across your tracked landscape.