dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Caching

Understand

Autoregressive Models (ARMs) have long dominated the landscape of Large Language Models.

• Recently, a new paradigm has emerged in the form of diffusion-based Large Language Models (dLLMs), which generate text by iteratively denoising masked segments.
• This approach has shown significant advantages and potential.
• However, dLLMs suffer from high inference latency.