Semiconductor News & Analysis Feed

OpenAI and Broadcom unveiled Jalapeño, an LLM-optimized inference accelerator, in just nine months from initial design to tape-out—a timeline that challenges industry norms for high-performance ASIC development. This achievement highlights the growing role of AI in chip design, with OpenAI's own mod

OpenAI and Broadcom have unveiled Jalapeño, their first custom AI chip, claiming a 50% reduction in inference costs. Designed in-house by OpenAI and manufactured by TSMC on its 3nm node, the chip is optimized for running large language models and aims to reduce reliance on NVIDIA. While early lab te

OpenAI has unveiled its custom-designed AI inference chip, named Jalapeño, set for deployment at 'Gigawatt scale' with data center partners across multiple generations. While the company did not specify against which technology it is benchmarking performance, it claims the first-generation accelerat

OpenAI's announcement of its custom-built chip, Jalapeño, marks a significant strategic move toward vertical integration in the AI hardware space. Designed as an Application-Specific Integrated Circuit (ASIC) to accelerate AI inference, Jalapeño represents a shift from reliance on third-party hardwa

OpenAI and Broadcom have unveiled their custom AI chip, named 'Jalapeño,' designed for inference tasks and reportedly matching the performance of NVIDIA’s Blackwell chips and Google’s TPUs. Manufactured by TSMC, the chip is set for deployment by year-end in servers made by Celestica. This move under

Broadcom and OpenAI have unveiled Jalapeño, a new AI chip specifically designed for large language model (LLM) inference, intensifying competition in the AI chip market. Developed through a close collaboration, the chip was designed by OpenAI and industrialized by Broadcom and Celestica, with the en

Broadcom and OpenAI have unveiled the Jalapeño, a custom-built inference processor designed specifically for large language models and future agentic AI workloads. Unlike general-purpose or repurposed training accelerators, Jalapeño is a purpose-built ASIC optimized for inference efficiency, address

OpenAI has unveiled its 'Jalapeño' intelligence platform, powered by Broadcom hardware and featuring High Bandwidth Memory (HBM). This development underscores a significant advancement in AI computing infrastructure, with HBM enabling faster data transfer and improved energy efficiency—crucial for l

Broadcom and OpenAI have jointly unveiled Jalapeño, a new AI chip designed to accelerate large language model inference. This collaboration underscores a growing trend in the semiconductor industry, where specialized chips are becoming essential for AI workloads. Jalapeño is purpose-built for effici