Jalapeño’s first results show industry-leading speed and efficiency in AI inference
ai
On Tuesday, OpenAI announced Jalapeño, a custom inference chip designed for faster and more power-efficient AI inference. The company says its first results show industry-leading speed and efficiency, with higher throughput and lower latency for modern models.
Source: https://openai.com/index/jalapeno-first-results
Listen to this story
Hear this and more stories in a personalized audio briefing.
Open The Chonkerton