ainewsblitz.com

Breaking

OpenAI and Broadcom’s Jalapeño inference chip aims to cut costs and loosen Nvidia’s hold

  • Infra & Chips
  • Sales & Business

OpenAI is building a custom inference accelerator with Broadcom, named Jalapeño, to lower hardware costs and protect margins as spending on running models climbs — a move that, on early measurements, could also reduce Nvidia’s leverage over one of its largest customers.

Continue reading

The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.

$20
Read this article
$29/month
Unlimited — all 27,510 articles, the full archive, and comprehension quizzes
Save 72%
$98/year
≈ $8.17/month
Unlimited, billed once a year