Alibaba's Zhenwu V900 AI chip to enter mass production in Q1
11/20/2026 — 11/20, 16:19·1 sources (all)·1 reports (all)
Key takeaways
- Alibaba Cloud said its next-generation AI chip, Zhenwu V900, will go into mass production and ship in the first quarter of next year, callin…
- supernodes built on it can scale to 500,000 cards per cluster.
Background & analysis
On November 20, 2026, IT之家 reported that Alibaba released its financial results for the second quarter of fiscal year 2027 (July 1, 2026 to September 30, 2026) on the evening of November 19. For that quarter, revenue from AI cloud and computing power services reached 609.73 billion yuan, up 53% year on year. Alongside the earnings release, Alibaba Cloud officially announced that its next-generation AI chip Zhenwu V900 will enter mass production and go on sale in the first quarter of next year, and described it as the most powerful self-developed AI chip in China in terms of computing performance.
According to the disclosure, Zhenwu V900 is a training and inference integrated AI chip whose computing power rises to 3x that of Zhenwu M890. It supports 216GB of memory, 1200GB/s of inter-chip interconnect, and FP8/FP4 precision. The new generation of Alibaba Cloud AI super nodes built on Zhenwu V900 adopts an AI data center network architecture newly designed by Alibaba Cloud, and a single cluster can scale to 500,000 cards. At present, the Alibaba Cloud self-developed AI super nodes equipped with Zhenwu M890 chips have been rolled out at scale, and Alibaba Cloud is already offering super node cloud services to customers in locations including Ulanqab and Zhongwei. Zhenwu V900 has not yet reached the mass production and sales stage.
AI-generated from 1 reports · updated 2 days ago
- Heat index
- 29
- All sources
- 1
- All reports
- 1
- First seen
- 2 days ago
Reports on this story headlines open the original
Alibaba Cloud says its next-generation AI chip, Zhenwu V900, will enter mass production and go on sale in the first quarter of next year, calling it the most powerful self-developed AI chip in China. The train-and-inference chip offers 3x the compute of Zhenwu M890, with 216GB of memory and 1200GB/s inter-chip bandwidth. New AI super nodes built on it can scale to 500,000 cards per cluster.
IT之家AI score 58
Other stories people are talking about
- Heat index 1143RisingAnthropic Reaches $1.6 Trillion Market Value in First Trading Week After IPO21 sources
- Heat index 1011Anthropic Mathematician Says Claude Formalized the Generalized Riemann Hypothesis21 sources
- Heat index 622Anthropic IPO total raise reaches $93.5 billion after greenshoe exercise20 sources
- Heat index 596RisingThinking Machines Lab Open-Sources Inkling 2 Mini with 32GB Model Card Recommendation10 sources
- Heat index 490RisingSEC probes Nvidia accounting practices as shares post seven-week slide9 sources
How is heat calculated?About the methodHide
Heat counts how many independent sources covered a story in the last 48 hours: one source counts once no matter how many posts it published, decaying with a 24-hour half-life. What ranks first is what many people are talking about.
This page aggregates public feeds. Headlines and summaries are machine-organized and remain the property of the original authors; verify important facts at the source. If you believe a headline or summary infringes your rights, email the contact address in the footer with the page URL and basis of your claim, and we will remove or replace it after review.
- Surge
- Discussion rising fast
- New
- First report within 6 hours
- Rising
- Still gathering discussion

