AMD acquires Taalas, a startup that bakes AI models directly into silicon

https://the-decoder.com/wp-content/uploads/2026/07/amd_logowall.png" style="height: auto; margin-bottom: 10px;" width="2048" />

AMD is buying Canadian startup Taalas, which hard-codes model weights directly into inference chips.

That makes them extremely fast but locks each chip to a single model.

A demo chip hit over 16,000 tokens per second per user running Llama 3.1-8B. Google is reportedly working on a similar approach for Gemini.

The article https://the-decoder.com/amd-acquires-taalas-a-startup-that-bakes-ai-models-directly-into-silicon/">AMD acquires Taalas, a startup that bakes AI models directly into silicon appeared first on https://the-decoder.com">The Decoder.