PartnershipJun 24, 2026, 09:02 AM
Broadcom, OpenAI Unveil Jalapeño AI Chip for LLM Inference
AI Summary
Broadcom Inc. and OpenAI announced the unveiling of Jalapeño, OpenAI’s first Intelligence Processor. This AI accelerator, co-developed in just nine months, is designed specifically for LLM inference and is the first in a multi-generation compute platform. Early tests suggest Jalapeño will deliver significantly better performance per watt than current state-of-the-art solutions. The chip is intended for deployment at gigawatt scale with data center partners, with initial rollout expected by the end of 2026, aiming to make advanced AI faster, more reliable, and more accessible.
Key Highlights
- Broadcom and OpenAI unveiled Jalapeño, OpenAI’s first Intelligence Processor.
- Jalapeño is an AI accelerator designed for LLM inference, co-developed in nine months.
- Early testing indicates performance per watt substantially better than current state-of-the-art.
- It is the first AI accelerator in a multi-generation compute platform built by the companies.
- The chip is designed for deployment at gigawatt scale with data center partners.
- Initial deployment of the platform is targeted by the end of 2026.
- Broadcom provides silicon implementation and networking technologies for the platform.
Price Impact
More from AVGO