DARTree: Speculative Diffusion Decoding with Autoregressive Draft Trees

Speculative decoding losslessly accelerates autoregressive language models by verifying multiple draft tokens in parallel.

Speculative decoding losslessly accelerates autoregressive language models by verifying multiple draft tokens in parallel. Diffusion-based drafters further reduce proposal latency by predicting an entire token block in parallel, but their position-wise distributions are marginal…