NVIDIA announced the release of Dynamo-optimized deployment recipes for Korea’s leading open models, including A.X K2, K-EXAONE 2.0, Solar Open 2, and Motif-3. These recipes are optimized for NVIDIA B200 GPUs and deliver up to 2x performance out of the box, helping developers bring these models into production faster.
What happened
NVIDIA is releasing Dynamo-optimized deployment recipes for Korea’s leading open models, including A.X K2 from SK Telecom, K-EXAONE 2.0 from LG AI Research, Solar Open 2 from Upstage, and Motif-3 from Motif Technologies. As models grow beyond the capacity of a single GPU, they must be split across multiple GPUs, requiring careful coordination of request routing and communication to maintain performance. NVIDIA Dynamo is an open source, distributed inference-serving framework built to deploy models in multi-node environments at data center scale. It handles this routing and communication to maximize inference performance. Optimized for NVIDIA B200 GPUs, these recipes take the guesswork out of deployment, delivering up to 2x performance out of the box. They help developers bring Korea’s open models into production faster and turn them into broadly accessible AI for All services.
What to weigh
- These recipes are optimized for NVIDIA B200 GPUs.
- The recipes help developers bring Korea’s open models into production faster.
FAQ
Which models are supported by the Dynamo recipes?
The Dynamo recipes support A.X K2 from SK Telecom, K-EXAONE 2.0 from LG AI Research, Solar Open 2 from Upstage, and Motif-3 from Motif Technologies.
What is the performance improvement provided by the recipes?
The recipes deliver up to 2x performance out of the box.
What is the purpose of NVIDIA Dynamo?
NVIDIA Dynamo is an open source, distributed inference-serving framework built to deploy models in multi-node environments at data center scale.
Source: NVIDIA