Preprint
Oct 2026
DWISE: Denoising Workload-Informed Scheduling Engine
Unlike autoregressive large language models (AR-LLMs), diffusion LLMs (dLLMs) generate text by iteratively denoising many tokens in parallel, offering a promising path to efficient inference. Existing serving frameworks, however, schedule dLLM requests with policies designed for AR models, namely first-come-first-serve...
Lie Li, Wen Li, Jun-Xiao Shen et al.
· 0 citations