AMD acquires Toronto-based Taalas, which integrates model weights directly into silicon to boost inference performance, for an undisclosed sum (Tobias Mann/The Register)
AMD acquired Taalas to add silicon-level model-weight integration for faster AI inference hardware.
Excerpt
<a href="https://www.theregister.com/systems/2026/08/06/amd-acquires-ai-chip-startup-taalas-to-boost-inference-performance-by-etching-models-into-silicon/5284344"><img align="RIGHT" border="0" hspace="4" src="http://www.techmeme.com/260806/i45.jpg" vspace="4" /></a>
<p><a href="https://www.techmeme.com/260806/p45#a260806p45" title="Techmeme permalink"><img height="12" src="http://www.techmeme.com/img/pml.png" style="border: none; padding: 0; margin: 0;" width="11" /></a> Tobias Mann / <a href="https://www.theregister.com/">The Register</a>:<br />
<span style="font-size: 1.3em;"><b><a href="https://www.theregister.com/systems/2026/08/06/amd-acquires-ai-chip-startup-taalas-to-boost-inference-performance-by-etching-models-into-silicon/5284344">AMD acquires Toronto-based Taalas, which integrates model weights directly into silicon to boost inference performance, for an undisclosed sum</a></b></span> — Early tech demos show model-specific integrated circuits churning out up to 17,000 tokens a second — In AMD's latest bid to upset Nvidia's dominance … </p>
Read at source: https://www.techmeme.com/260806/p45#a260806p45