Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

Zhenwu J900

AI overview

Sign in and the AI will write an overview from our coverage.

Headlines · 1

  1. Alibaba accelerates T-Head's third-generation AI chip roadmap

    Alibaba CEO Wu Yongming said T-Head's third-generation GPU roadmap is advancing, with Zhenwu M890 fully deployed and Zhenwu V900 and J900 scheduled for large-scale production in 2027 and 2028, respectively. Alibaba Cloud said V900 will enter mass-production sales in Q1 2027, describing it as a training-and-inference chip with 216GB of memory, 1,200GB/s chip-to-chip bandwidth and FP8/FP4 support. The company also described a V900-based AI supernode designed to scale one cluster to 500,000 cards, while Wu said Qwen has trained its next-generation model on T-Head chips and Bailian offers inference services based on domestic chips.

    36氪快讯 · 🔥 7

Experience and discussion from the community

Share my Zhenwu J900 experienceAsk about Zhenwu J900

Nobody has shared their experience with Zhenwu J900 yet.