The BuildJune 24, 2026via SiliconAngle
OpenAI, Broadcom debut custom Jalapeño chip for AI inference
Why it matters
OpenAI's move into custom silicon with Broadcom signals a critical shift: leading AI labs are now building their own hardware to reduce dependency on NVIDIA, cut costs, and optimize inference at scale. This is infrastructure consolidation, not a one-off experiment.
Key signals
- OpenAI + Broadcom partnership on custom Jalapeño chip for inference
- Broadcom prior experience: designed Google TPU line
- Chip targets LLM inference workloads
- Signals vertical integration into custom silicon
- Reduces reliance on third-party GPU suppliers
The hook
OpenAI just stopped waiting for NVIDIA. Meet Jalapeño—the custom chip that changes the inference game.
OpenAI Group PBC today revealed a custom chip called Jalapeño that it will use to power its large language models. The processor is the fruit of a collaboration with Broadcom Inc., which is no stranger to custom silicon design. The company helped Google LLC develop its TPU line of artificial intelligence accelerators. In April, the […]