OpenAI introduces Jalapeño AI processor

OpenAI has announced the development of the first custom processor designed to run large AI models, in collaboration with Broadcom. Named Jalapeño, it is primarily used to enhance the speed and responsiveness of language models such as ChatGPT and Codex. The processor focuses on the inference stage rather than training, aiming to improve energy efficiency and reduce response times. Early indications suggest higher efficiency levels, and deployment is expected to begin before the end of 2026. This development represents a step toward building an integrated computing platform that evolves across multiple generations to support future AI models.

articleDetails.fontSize.sizeحجم النص

تنويه: هذا ملخص تم إنشاؤه بواسطة الذكاء الاصطناعي

عرض المقال بالكامل