OpenAI
AI · Infrastructure
Broadcom, OpenAI debut Jalapeño LLM inference chip for hyperscale AI
June 24, 2026
Broadcom and OpenAI unveiled Jalapeño, a custom LLM inference accelerator co-designed by OpenAI and built by Broadcom, with initial data center deployment targeted for late 2026.
Read the Full Story in Velocity
Get curated startup and tech news with new stories published daily, company insights, and real-time alerts.