"A blank-slate design for modern LLM inference, not a general-purpose accelerator adapted from earlier AI workloads"
"A blank-slate design for modern LLM inference, not a general-purpose accelerator adapted from earlier AI workloads"
June 24, 2026
By
Have your say
OpenAI and Broadcom have debuted their first co-designed AI chip of a planned multi-generation compute platform.'Jalapeño' is set to be OpenAI’s first Intelligence Processor, designed for large language model inference.
OpenAI is adding custom hardware to its tech stack. The "Jalapeño" chip, developed with Broadcom, is tailored for large language…
Is the world's leading AI software company getting ready to challenge the tech industry's biggest hardware giants? OpenAI and…
The companies attributed this speed to a deep software-hardware co-development process that actively used OpenAI’s own models to…
OpenAI, Broadcom debut custom Jalapeño chip for AI inference - SiliconANGLE
Firms fail to disclose (m)any details.
Named Jalapeño, the new processor was designed specifically for the unique needs of OpenAI's inference systems.
