OpenAI says Jalapeno chip outperformed Nvidia in tests

OpenAI says Jalapeno chip outperformed Nvidia in tests

The custom processor led Nvidia’s GB300 in power efficiency and response speed, with OpenAI planning to use it for AI models later this year.

OpenAI said its new Jalapeno processor outperformed Nvidia’s current lineup in tests, Bloomberg reported.

Advertisement

The chip led Nvidia’s GB300 in two categories: the amount of AI work it could handle per unit of power and the speed at which it returned responses. OpenAI chip chief Richard Ho said the comparison used a public benchmarking system.

OpenAI plans to begin using Jalapeno to support its AI models later this year as it expands in-house chip development. The company expects the processor to reduce costs if production can be scaled.

OpenAI developed Jalapeno with Broadcom. The chip is designed to offer both high-throughput performance and low latency, allowing OpenAI to choose between lower operating costs and faster responses for different models.

Disclosure: This article was edited by Editorial Team. For more information on how we create and review content, see our Editorial Policy.
OpenAI says Jalapeno chip outperformed Nvidia in tests
OpenAI says Jalapeno chip outperformed Nvidia in tests

The custom processor led Nvidia’s GB300 in power efficiency and response speed, with OpenAI planning to use it for AI models later this year.

Share

Add us on Google

OpenAI said its new Jalapeno processor outperformed Nvidia’s current lineup in tests, Bloomberg reported.

Advertisement

The chip led Nvidia’s GB300 in two categories: the amount of AI work it could handle per unit of power and the speed at which it returned responses. OpenAI chip chief Richard Ho said the comparison used a public benchmarking system.

OpenAI plans to begin using Jalapeno to support its AI models later this year as it expands in-house chip development. The company expects the processor to reduce costs if production can be scaled.

OpenAI developed Jalapeno with Broadcom. The chip is designed to offer both high-throughput performance and low latency, allowing OpenAI to choose between lower operating costs and faster responses for different models.

Disclosure: This article was edited by Editorial Team. For more information on how we create and review content, see our Editorial Policy.