OpenAI and Broadcom unveil AI chip called Jalapeño
Get Alerts AVGO Hot Sheet
Overall Analyst Rating:
SELL (= Flat)
Dividend Yield: 0.6%
Revenue Growth %: +83.2%
Join SI Premium – FREE
OpenAI and Broadcom (NASDAQ: AVGO) have unveiled a custom AI accelerator chip called Jalapeño, designed specifically for large language model (LLM) inference. According to a joint press release, the chip was developed from initial design to manufacturing tape-out in nine months.
The chip is described as OpenAI's first Intelligence Processor and is intended for deployment at gigawatt scale with data center partners, including Microsoft, beginning in 2026. Celestica is also named as a partner, contributing board, rack, and system integration expertise.
Engineering samples of the Jalapeño chip are running machine learning workloads in the lab, including GPT-5.3-Codex-Spark, at production target frequency and power. OpenAI said early testing indicates the chip will deliver performance per watt better than what it describes as current state-of-the-art, though final performance measurements are still ongoing. A detailed technical performance report is expected in the coming months.
The chip's architecture is designed to reduce data movement and balance compute, memory, and networking resources. Broadcom's Tomahawk networking silicon is part of the platform.
"By co-developing our industry-leading silicon directly with OpenAI, we are enabling the deployment of gigawatt scale data centers with Microsoft and other partners beginning in 2026," said Hock Tan, President and CEO of Broadcom.
OpenAI President Greg Brockman described the chip as part of a "long-term full-stack infrastructure strategy," stating the goal is to make compute more abundant and AI more affordable.
Richard Ho, who leads OpenAI's hardware program, said the architecture was optimized around "kernels, memory movement, networking, and serving patterns that matter most for frontier AI models."
Jalapeño is positioned as the first step in a multi-generation compute platform, with subsequent generations planned for the years following the initial 2026 deployment.
Serious News for Serious Traders! Try StreetInsider.com Premium Free!
You May Also Be Interested In
- Apple suing OpenAI over alleged misappropriation of trade secrets
- GuideAI Health hires firms for marketing and investor outreach
- Faraday Future cancels ~49.9M warrants, restructures July financing
Create E-mail Alert Related Categories
Corporate News, Hot Corp. NewsRelated Entities
Maynard Um, Mark Zuckerberg, ARKSign up for StreetInsider Free!
Receive full access to all new and archived articles, unlimited portfolio tracking, e-mail alerts, custom newswires and RSS feeds - and more!



Tweet
Share