Tag
LaCache introduces a training-free acceleration framework for diffusion-based LLMs that uses lossless caching and precision-adaptive inference to eliminate redundant computation during denoising steps, achieving up to 40.2× end-to-end speedup while maintaining task accuracy.
This paper identifies evaluation inconsistencies in diffusion LLM decoding methods, showing that prompt template choice significantly impacts rankings, and proposes guidelines for reliable evaluation.
This paper proposes FAIR-Calib, a two-stage post-training quantization framework for diffusion large language models that addresses the instability of token commitments during iterative refinement. It achieves state-of-the-art results on LLaDA and Dream models under low-bit quantization.
This paper proposes dMoE, a block-level mixture-of-experts framework for diffusion large language models that aggregates token-level expert distributions into block-level routing, reducing activated experts and memory usage while maintaining performance.