Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding
Paper
•
2505.22618
•
Published
•
42
dLLM
-
-
DINGO: Constrained Inference for Diffusion LLMs
Paper • 2505.23061 • Published • 31 -
Discrete Diffusion in Large Language and Multimodal Models: A Survey
Paper • 2506.13759 • Published • 43 -
LongLLaDA: Unlocking Long Context Capabilities in Diffusion LLMs
Paper • 2506.14429 • Published • 45 -
Beyond Fixed: Variable-Length Denoising for Diffusion Large Language Models
Paper • 2508.00819 • Published • 62 -
Sparse-dLLM: Accelerating Diffusion LLMs with Dynamic Cache Eviction
Paper • 2508.02558 • Published • 9 -
Seed Diffusion: A Large-Scale Diffusion Language Model with High-Speed Inference
Paper • 2508.02193 • Published • 126 -
Time Is a Feature: Exploiting Temporal Dynamics in Diffusion Language Models
Paper • 2508.09138 • Published • 34 -
Diffusion LLMs Can Do Faster-Than-AR Inference via Discrete Diffusion Forcing
Paper • 2508.09192 • Published • 29 -
A Survey on Diffusion Language Models
Paper • 2508.10875 • Published • 31