OpenAI's Jalapeño Chip Takes Aim at Nvidia's Dominance in AI Inference
This story is only covered by news sources that have yet to be evaluated by the independent media monitoring agencies we use to assess the quality and reliability of news outlets on our platform. Learn more here.3 Articles
3 Articles
OpenAI lifts the lid on its in-house Jalapeño chip - with benchmarks claiming it beats Nvidia's GB300
OpenAI says its 700W Jalapeño chip beats Nvidia's 1,400W GB300 in efficiency, while skipping a crucial head-to-head against the latter's Vera Rubin architecture.
OpenAI and Broadcom have developed the Jalapeño chip to optimize the inference of large language models (LLM). This chip surpasses the current solutions of Nvidia and AMD thanks to a generalist architecture focusing on energy efficiency and exceptional performance/watt ratio. The development has been accelerated by the use of AI for hardware design and automatic generation of software kernels via Codex. With Jalapeño, OpenAI calls into question …
OpenAI advances in the design of its own processors with Jalapeño, but Jensen Huang argues that Nvidia retains decisive advantages in scale, supply and technology. *** Jensen Huang stated that he does not personally take the development of Jalapeño and defended Nvidia’s ability to compete. OpenAI said that his inference chip exceeded Nvidia’s GB300 in response speed and energy efficiency, according to his own tests. Nvidia reported revenues of U…
Coverage Details
Bias Distribution
- 100% of the sources are Center
Factuality
To view factuality data please Upgrade to Premium
