OpenAI and Broadcom unveil LLM-optimized inference chip
OpenAI and Broadcom introduce Jalapeño, a custom AI chip built for LLM inference to improve performance, efficiency, and scale across AI systems.
Get smart on it
OpenAI and Broadcom have unveiled an AI accelerator chip designed specifically for running large language models, marking OpenAI's expansion into hardware manufacturing alongside its models and products. The chip was developed in nine months through close collaboration between the companies and is designed to deliver substantially better performance per watt than current alternatives while working with LLMs across the industry. The companies plan to deploy the chip at large scale in data centers across multiple generations, with the goal of making advanced AI faster, more reliable, and more affordable for broader access. This represents part of OpenAI's strategy to control its full infrastructure stack, from chip design through models to products, in order to optimize efficiency throughout the system.
Related news
OpenAI and Broadcom announce chip designed for LLM inference at scale
OpenAI, the company behind ChatGPT and Codex and the models those tools utilize, and Broadcom, an established silicon supplier, have announced a new chip called Jalapeño, designed specifically for large language model inference in data centers. The chip is intended to be deployed at large data centers, both companies claim this is just the first generation in a long-term project that will see chips refined over time.Read full article Comments
Cerebras stock plunges after earnings as CEO says margin outlook was misunderstood
In its first earnings report since going public, the AI chipmaker forecast a narrower gross margin in its core business, scaring investors.
