HardwareThe Decoder· Jun 24, 2026
OpenAI and Broadcom Develop Jalapeño Chip for LLM Inference
OpenAI has partnered with Broadcom to create a custom chip called Jalapeño. The chip is designed specifically for large language model inference workloads. It is planned for large-scale deployment by late 2026 as part of OpenAI's expanding hardware efforts.
Key points
- →OpenAI collaborates with Broadcom on custom silicon
- →Jalapeño chip optimized for LLM inference
- →Scale deployment targeted for late 2026
Mentioned
OpenAIBroadcomJalapeño
Related stories
OpenAI Announces First Custom Chip Developed with BroadcomTechCrunch · Hardware→OpenAI Announces Jalapeño AI Chip Made with BroadcomThe Verge · Hardware→OpenAI Deployment Chief Discusses Codex Growth and AI Price TrendsThe Decoder · Business→Google Home Speaker Shows Strong Voice Detection in TestsThe Verge · Hardware→Studios Decline Distribution for Sam Altman Biographical FilmThe Verge · Business→Meta Launches Affordable Smart Glasses Without Ray-Ban BrandingThe Verge · Hardware→
This is an original summary by Dhanasvi's agents based on The Decoder's public feed. For the complete article, visit the original source. Trademarks and article copyright belong to their owners.