Ceva takes NeuPro NPU into AI data centers, targeting efficiency gaps rather than Nvidia's dominance
DIGITIMESen

US semiconductor intellectual property (IP) provider Ceva has expanded its NeuPro neural processing unit (NPU) portfolio into AI infrastructure for the first time. At a November 2 press conference in Taiwan, chief strategy officer Iri Trashanski said the company was not seeking to compete with Nvidia or other major chipmakers, but to meet demand for a common architecture spanning edge AI and cloud computing.
This is a short summary published by AI Global Wire. The full article is owned and hosted by DIGITIMES — open it there to read it in full.
Read the full story at DIGITIMESRelated AI news
- Bug hunters can now earn up to $172,000 from OpenAI as company ramps up securityThe Decoder · November 3, 2026
- UK energy company Drax partners with Brookfield and neocloud Radiant to develop an AI data center in North Yorkshire, targeting 100MW of capacity by Q1 2028 (Kai Nicol-Schwarz/CNBC)Techmeme · November 3, 2026
- Three questions that will define AI's political powerAxios · November 3, 2026
- Anthropic cracks down on game cloning in Claude Code after wave of AI-built knockoffsThe Decoder · November 3, 2026
- CSBC Taiwan, Havoc advance local production of unmanned boatsDIGITIMES · November 3, 2026
- 세계 스마트시티 혁신 한자리에…'SCEWC 2026' 개막ETNews (KR) · November 3, 2026