A.X K2

NVIDIA released Dynamo-optimized deployment recipes for four leading Korean open models: SK Telecom's A.X K2, LG AI Research's K-EXAONE 2.0, Upstage's Solar Open 2 and Motif-3. Tuned for B200 GPUs, the recipes claim up to 2x out-of-the-box performance, with Dynamo serving as the open-source distributed inference framework handling routing and communication across multi-node deployments.