OpenAI, Broadcom team up on Jalapeño LLM inference chip platform

Broadcom Limited

Broadcom Limited

AVGO

0.00

  • Broadcom partnered with OpenAI to co-develop Jalapeño, an LLM-inference intelligence processor, as the first chip in a multi-generation compute platform.
  • The program targets gigawatt-scale deployment with data center partners starting in 2026, aiming to improve performance per watt versus current leading accelerators.
  • Engineering samples are running ML workloads at target frequency and power, including GPT-5.3-Codex-Spark, with final performance still being measured.
  • The chip moved from initial design to tape-out in nine months, supported by Broadcom silicon implementation and networking technology, including Tomahawk.


Disclaimer: This news brief was created by Public Technologies (PUBT) using generative artificial intelligence. While PUBT strives to provide accurate and timely information, this AI-generated content is for informational purposes only and should not be interpreted as financial, investment, or legal advice. Broadcom Inc. published the original content used to generate this news brief via GlobeNewswire (Ref. ID: 202606240900PRIMZONEFULLFEED9751687) on June 24, 2026, and is solely responsible for the information contained therein.