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
- US AI and data center investment to hit 3.63% of GDP yearly, topping the 1800s railroad boom — McDonaghMatthew · 2026-09-26
- Paper: AI buildout to cost $10.3T over 8 years, needs $3.7T annual revenue by 2032 — AccBalanced · 2026-09-26
- Starlink to double maritime speeds to near 1 Gbps by end of December, no new dish needed — XFreeze · 2026-09-26
- News site logs show AI bots hitting it hundreds of thousands of times a day — PJZNY · 2026-09-26
- Why Anthropic lags OpenAI on math: compute constraints and 400k GPUs coming online — haider1 · 2026-09-26
- Unverified: OpenAI halted training of its top upcoming model after Sept 20 incident — ccerrato147 · 2026-09-26