← Front page

Invest Like the Best with Patrick O'Shaughnessy · Tuesday, June 30, 2026

Etched's Integrated Inference Solution: Chip to Rack

Etched is not just building a chip, but a complete inference solution including the chip, power delivery, boards, interconnects, and production. They focus on optimizing both the pre-fill and decode stages of AI inference, differentiating their approach from traditional GPU architectures.

personRob LockencompanyEtched

The tape

3 quotes
We're not just building a chip. We're building a full inference solution. And that means rack. That means the chip, that means the power delivery into the chip, that means the board on which it sits, that means the interconnects, the chip talks to each other.
Rob Locken
We think about how we get an advantage. There are two key parts of running inference: there's pre-fill and decode.
Rob Locken
Now, we have two key tech bets in both of these things.
Rob Locken
Heard on Invest Like the Best with Patrick O'Shaughnessy — “Etched - Building AI Hardware to Make Inference Faster and Cheaper - [Invest Like the Best, EP.480], published Tuesday, June 30, 2026. Heardvine summarizes and quotes with attribution and timestamps, and links to the original everywhere.
Transcribed via Gemini audio transcription · $0.08
Etched's Integrated Inference Solution: Chip to Rack — Heardvine