# AI Chip Startup Etched Completes Tape-Out, Secures $800 Million in Funding

- Category: Flash (快讯)
- Published: 2026-07-01T11:54:00.000Z
- Source date: 2026-07-01
- HTML: https://www.88z.ai/en/news/flash-20260701-e146cbeb30f75445
- Markdown: https://www.88z.ai/en/news/flash-20260701-e146cbeb30f75445.md
- Other language: https://www.88z.ai/news/flash-20260701-e146cbeb30f75445.md

Transformer-specific AI chip startup Etched has completed the tape-out of its A0 chip, securing $800 million in funding and $1 billion in customer orders. Founded by a Harvard dropout, the company is backed by AI luminaries including Karpathy, Li Fei-Fei, and Hinton. Etched has launched its first rack product, utilizing Low Voltage Inference and Cluster-Scale Memory technologies optimized for trillion-parameter MoE model inference, with shipments planned for this summer.

## At a glance

- Etched completes A0 chip tape-out, securing $800M funding and $1B in orders
- First rack product uses LVI and CSM tech, optimized for trillion-parameter MoE inference

## The update

Etched, an AI chip startup focused on the Transformer architecture, recently announced that its first A0 chip has successfully completed tape-out. Concurrently, the company closed an $800 million funding round and secured $1 billion in customer orders. Founded by a Harvard dropout, Etched boasts an impressive investor lineup featuring prominent AI experts such as Karpathy, Li Fei-Fei, and Hinton. On the hardware front, Etched has launched its first rack-based solution. This product integrates two core technologies: Low Voltage Inference and Cluster-Scale Memory, specifically deep-optimized for inference of Mixture of Experts models with trillion-level parameters. According to plans, this series of products will be officially delivered to customers this summer.

## Sources

- [量子位](https://mp.weixin.qq.com/s/ST38chCPQ5kQt_P9ilKCfA) (2026-07-01)

This article is an AI-assisted synthesis by 88Z AI based on the public sources below. Product claims and availability are attributed to their publishers. It does not represent independent testing or first-hand reporting.