Microsoft Azure hits 1.1 million token/sec AI inference record

4 hours ago 1
Machine Learning. AI Neural Network Concepts

Microsoft (MSFT) said it has achieved a new AI inference record, with its Azure ND GB300 v6 virtual machines processing 1.1 million tokens per second on a single rack powered by Nvidia (NVDA) GB300 GPUs.

The performance test, conducted using the

Recommended For You

More Trending News

Read Entire Article