AMD acquires Taalas to etch AI models into silicon, boosting inference 48x

AMD acquires Taalas to boost inference performance by etching models in silicon

AMD has acquired AI chip startup Taalas, which bakes model weights directly into silicon to dramatically speed up inference. Taalas's first chip, the HC1, served Meta's Llama 3.1 8B at 16,960 tokens per second—48x faster than Nvidia's GPUs. The technology, called model-specific integrated circuits (MSICs), requires re-spinning chips for new models, but only two metal layers need changing. AMD plans to pair Taalas chips with its Instinct-based Helios racks, potentially enabling disaggregated architectures where GPUs handle prompt processing and Taalas accelerators handle token generation.