TL;DR: Today’s Best LLMs mostly decode autoregressively from left-to-right, which gives great quality but is terribly slow. Diffusion LLM can decode many tokens in parallel thanks to their non-casual, any-order generation, but they must be trained from scratch, or heavily adapted from autoregressive (AR) checkpoints with a non-casual diffusion objective; we find this mismatch often hurts quality and breaks many effective KV-cache related serving optimizations. This blog introduces Jacobi Forcing, a new training technique that converts LLMs into native casual parallel decoders. Jacobi forcing keeps the casual AR backbone and fixes the AR-to-diffusion mismatch by training the model to handle noisy future blocks along its own Jacobi decoding trajectories. This yields an AR model which behaves like a diffusion-style decoder—decoding multiple tokens per pass, but still from left to right—with up to $4.5\times$ higher tokens-per-forward and $4\times$ wall-clock speedup on coding and math tasks, while retraining near-AR generation quality.