SpecFold: Folding Multi-Branch Redundancy for Faster Speculative Decoding in Diffusion Language Models
SpecFold reuses multi-branch computation to speed diffusion-LLM speculative decoding by up to 1.99×.
1 stories, newest first · one card per story
SpecFold reuses multi-branch computation to speed diffusion-LLM speculative decoding by up to 1.99×.
Today 1.5K readers · 2.4K views · 757 reads · all time 189K views