Accelerating Diffusion LLMs via Adaptive Parallel Decoding
arxiv.org · 7,032 words · saved by 1 readers
N/A
Accelerating Diffusion LLMs via Adaptive Parallel Decoding Daniel Israel Guy Van den Broeck Department of Computer Science Department of Computer Science University of California, Los Angeles University of California, Los Angeles disrael@cs.ucla.edu…
related reading
- Fast Inference from Transformers via Speculative Decodingarxiv.org
- Large Language Diffusion Modelsarxiv.org
- Speculative Decoding - philkravphilkrav.com
- Fast Inference from Transformers via Speculative Decodingarxiv.org
- 2409.02908arxiv.org
- Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decodingarxiv.org
- Diffusion will be everywherevarunneal.github.io
- Looking back at speculative decodingresearch.google
- Fast Inference from Transformers via Speculative Decodingarxiv.org
- 2503.09573arxiv.org
- Speculative Decoding: How It Evolved, When It Stays Lossless, and What's Nextneurips2026-speculative-decoding.vercel.app
- Self-Adapting Language Modelsarxiv.org