Author: Evolving AI - Bewertung: 6x - Views:32
OpenAI just revealed its own custom AI chip, and NVIDIA may finally have a serious reason to pay attention. Built with Broadcom, OpenAI’s new Jalapeño Intelligence Processor is a custom ASIC designed specifically for AI inference the process behind every ChatGPT response, Codex output, and API request. According to the companies, the chip was developed from scratch in roughly 9 months, with OpenAI using its own AI models to accelerate the hardware design process. The chip is manufactured on TSMC’s 3nm process and is reportedly already running real OpenAI workloads in the lab. Broadcom says early results show major cost savings compared with traditional AI GPUs, while OpenAI claims improved performance per watt. But this is bigger than one chip. Google has TPUs, Amazon has Trainium and Inferentia, Meta has MTIA, Microsoft has Maia, and now OpenAI has Jalapeño. The world's biggest AI companies are all trying to reduce their dependence on NVIDIA. So is OpenAI’s new AI chip the beginning of the end for NVIDIA’s dominance, or just the first step in a much longer hardware war?
#OpenAI #Nvidia #AIChips #Broadcom #ChatGPT #ArtificialIntelligence #Semiconductors
SOCIAL SHARE CARD GENERATOR