Jalapeño Demonstrates the Power of LLMs in Chip Design
OpenAI's Jalapeño chip showcases the power of LLMs in accelerating chip design.
On August 25, OpenAI unveiled Jalapeño, its first AI accelerator chip, boasting 13.4 petaflops of 4-bit compute and 232 gigabytes of advanced memory. Jalapeño can reduce end-to-end latency by up to 3.6 times compared to Nvidia's GB300. The chip's design was accelerated by OpenAI's large language models, completing the process from initial concept to silicon in under 20 months.
This synthesis was produced from its source by AI; there is no human editor or manual review step. How we work