Hacker News
Linking pages
- GitHub - NVIDIA/TransformerEngine: A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper and Ada GPUs, to provide better performance with lower memory utilization in both training and inference. https://github.com/NVIDIA/TransformerEngine 0 comments
Related searches:
Search whole site: site:inflection.ai
Search title: Inflection-2: The Next Step Up
See how to search.