Jun-Pan Wu

Step-dLLM: Adaptive Step-aware Sparse Attention for Efficient Diffusion LLM Inference

Diffusion large language models (dLLMs) generate tokens in parallel via iterative denoising, but their bidirectional attention prevents the KV caching used by autoregressive models and recomputes the full attention map at every step, incurring quadratic per-step cost. Existing sparse attention methods for dLLMs constru...