Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding
arxiv.org · 4,873 words · saved by 1 readers
N/A
2025-7-4 Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding Chengyue Wu1,2* Hao Zhang2* Shuchen Xue4 Zhijian Liu2 Shizhe Diao2 Ligeng Zhu2 Ping Luo1 Song Han2,3 Enze Xie2 1 2 3 4 The University of Hong Kong…
related reading
- Fast-dLLM v2nvlabs.github.io
- Large Language Diffusion Modelsarxiv.org
- Fast Inference from Transformers via Speculative Decodingarxiv.org
- Accelerating Diffusion LLMs via Adaptive Parallel Decodingarxiv.org
- Speculative Decoding - philkravphilkrav.com
- Fast Inference from Transformers via Speculative Decodingarxiv.org
- LLM Inference Performance Engineering: Best Practices | Databricks Blogdatabricks.com
- ⭐️ Fast LLM Inference From Scratchandrewkchan.dev
- CreditDecoding: Accelerating Parallel Decoding in Diffusion Large Language Models with Trace Creditsarxiv.org
- Diffusion will be everywherevarunneal.github.io
- 2409.02908arxiv.org
- Orthrus: Memory-Efficient Parallel Token Generation via Dual-View Diffusionarxiv.org