Alibaba's Zhenwu V900 chip: 216GB memory, 500K-card clusters, 20GW cloud goal
shashib · x · 2026-09-26
- Alibaba's T-Head unveiled the Zhenwu V900 accelerator at Apsara: 216GB memory, 1.2TB/s chip-to-chip bandwidth, FP8/FP4 support; CEO Eddie Wu calls it China's most powerful AI chip, claiming 3x the M890's performance.
- Mass production moved up to Q1 2027; an in-house interconnect switch can link 1,000+ cards, scaling clusters to 500,000 cards.
- Alibaba Cloud targets 20+ gigawatts of capacity by 2032, part of a strategy to keep training runs viable domestically; no FLOPS, process node, or foundry figures disclosed.
Related event: Alibaba Unveils T-Head Zhenwu V900 Accelerator Card(2 posts)→
More from Infra
- Running Qwen2.5-Coder-3B on Android: Jupyter + Pydantic Evals on-device eval pipeline — alex_b3b · 2026-11-11
- 22% of Nvidia revenue now books to Singapore, but only ~1% is local buyers — Gregory_C_Allen · 2026-11-11
- Huawei's Kirin 9050 NPU claims offline 30B MoE on smartphones, +140% perf — AIFlow_ML · 2026-11-11
- Stratechery: Intel vs AMD's diverging earnings and Intel's need for an old-new path — Stratechery · 2026-11-11
- a16z Podcast: Mike Volpi on What the 1990s Internet Boom Teaches Us About the AI Buildout — a16z Podcast · 2026-11-11
- Alibaba files to list chip-design unit T-Head in Hong Kong to fund AI push — pstAsiatech · 2026-11-11