Granite Switch 4.1: Chat, Decisions, and Speech from One Endpoint

Granite Switch 4.1 integrates chat, decision-making, and speech-to-text capabilities into a single model endpoint, using efficient adapters to enable fast switching and reduced GPU usage. It includes a new Decision aLoRA, a specialized Guardian aLoRA outperforming other safety models, and the fastest ASR model on OpenASR, all composable with the base model.