AI总结
核心结论
OpenAI与Broadcom合作开发名为“Jalapeño”的定制AI芯片，旨在提升大型语言模型（LLM）推理效率并降低运营成本，标志着OpenAI向全栈AI基础设施建设迈出重要一步。
结构逻辑
- 战略动向：OpenAI通过定制芯片减少对外部硬件供应商的依赖，实现从模型到硬件的全面掌控。
- 技术亮点：Jalapeño针对LLM的内存、网络及计算模式量身定制，性能/功耗比显著优于现有方案。
- 行业影响：反映了大型科技公司通过自研硬件来优化AI工作负载成本与性能的趋势。
- 未来规划：该项目是双方多代合作的开端，后续将有更多详细技术指标披露。
关键信息
- 核心概念：大语言模型推理（LLM Inference）、定制芯片（Custom Silicon）、全栈战略（Full-stack Strategy）。
- 主要公司：OpenAI、Broadcom (AVGO)。
- 行业背景：计算密集型经济（Compute-powered economy）。
关键问题与回答
- 问题：为何OpenAI要自研芯片？
- 回答：为降低推理成本、提升性能效率，并减少对外部供应商的长期依赖，建立自主掌控的AI计算基础设施。
正文
Illustration of the OpenAI logo on a screen, with a glowing keyboard in the background.
The custom chip marks the next step in the ChatGPT-parent’s strategy to build out a full stack behind its models and products. Dado Ruvic/Reuters
Quick Summary
- OpenAI and Broadcom collaborated to develop Jalapeño, a custom artificial-intelligence chip for large-language model inference.
- The Jalapeño chip was built from scratch to improve efficiency and lower costs for serving AI systems at scale.
- The project is part of OpenAI’s strategy to reduce reliance on external hardware and a multi-generation collaboration with Broadcom.
This summary was generated with AI and reviewed by an editor. about how we use artificial intelligence in our journalism.
OpenAI and Broadcom AVGO -0.83%decrease; down pointing triangle collaborated to develop a custom artificial-intelligence chip, marking the next step in the ChatGPT-parent’s strategy to build out a full stack behind its models and products.
The chip, called Jalapeño, was built from scratch specifically for large-language model inference, with the goal of improving efficiency and lowering the cost to serve AI systems at scale, the companies said Wednesday.
Early tests show that the chip will deliver performance per watt “substantially better” than current state-of-the-art chips, they added. OpenAI and Broadcom didn’t disclose specific performance measures but said a more-detailed technical report will be presented in the coming months.
Jalapeño was built around the memory, networking and compute patterns of large language models, rather than adapted from general-purpose architectures, according to the companies. It also reflects OpenAI’s broader effort to reduce reliance on external hardware suppliers and optimize infrastructure for its growing AI services.
“The world is moving to a compute-powered economy,” OpenAI President and Co-Founder Greg Brockman said. “By designing more of the stack ourselves, we can serve more intelligence with greater efficiency and keep pushing advanced AI toward broader access.”
Broadcom, which is providing silicon implementation and networking technology for the effort, said the project represents the start of a multi-generation collaboration aimed at building large-scale AI infrastructure.
The collaboration comes after OpenAI and Broadcom said last fall they were working together to develop and deploy 10 gigawatts of custom AI chips and computing systems over the next four years.
The move places OpenAI among a growing list of technology companies that are designing their own chips to better control the cost and performance of AI workloads.
Appeared in the June 25, 2026, print edition as ‘OpenAI, Broadcom Develop Custom Chip’.