Fast-dLLM

BlockServe, a continuous batching framework for diffusion large language models (dLLMs), achieves 1.9–10.6× throughput over Fast-dLLM across five benchmarks by integrating block-grained scheduling, mi…

Researchers have developed Fast-dLLM++, a training-free extension to diffusion large language models that accelerates inference by selecting parallel token commit sets based on the full sorted confide…