Nemotron Labs Diffusion merges auto‑regressive and diffusion for 6× faster LLM decoding
NVIDIA’s new Nemotron‑Labs‑Diffusion model combines autoregressive, diffusion, and self‑speculation decoding into a single architecture. By training with a joint objective, it can switch modes on the fly, delivering up to six times more tokens per forward pass than leading 8B LLMs while preserving accuracy. This boosts throughput for high‑concurrency deployments.