Search Results for "edition"

...Native Multi-Token Prediction accelerates inference through speculative decoding, and configurable thinking modes support direct responses or deeper reasoning. Unlike the NVFP4 edition, this BF16 release preserves full-precision weights for customization, domain adaptation, and model evaluation. It supports structured tool calling and deployment through vLLM and SGLang on NVIDIA GPUs, including configurations with four H100 or two GB200 accelerators.