Google advances Coral NPU with open architecture, compiler tools, and commercial chips for on-device AI
GoogleAI · x · 2026-10-23
Google announced a major step forward for Coral NPU, its blueprint for on-device AI hardware, adding an open architecture, compiler tooling, and commercial chips. Traditional chips waste battery moving data between memory and compute; Coral NPU computes where the data lives, giving wearables, smart sensors, and robots powerful local AI with minimal power draw. The unveiled architecture includes a RISC-V scalar core, a RISC-V RVV vector engine, and an outer-product MAC matrix engine, aiming to reduce fragmentation in edge AI development.
More from Embodied
- Embodied AI Makes Authority Physical: Robots Need an Inspectable Execution Trail — tallmetommy · 2026-10-23
- ROSCon 2026 talk videos are now available online — ___Mufasaa · 2026-10-23
- First Humanoid Hub Conference draws crowds with live humanoid demos — carlosdponx · 2026-10-23
- Modular low-cost UMI-style data collection rig inspired by fastumi and Kiwi — k7agar · 2026-10-23
- Universe badge pairs RP2350 with an AGENTS.md so Copilot can code and deploy to it — mariorod1 · 2026-10-23
- Hugging Face Hub launches OpenUSD support with 2,500+ NVIDIA SimReady assets — mishig25 · 2026-10-23