DFlow: Enabling Verifier Information Flow in Block Diffusion Speculative Decoding
Block diffusion speculative decoding improves LLM inference efficiency by proposing a block of future tokens in parallel and verifying them with a single forward pass through the target model. However, existing methods retain only the accepted prefix and discard the rejected suffix, preventing the computation spent on...
Yao-Jie Zhang, Lin-Feng Zhang, Bin Cui et al.
· 1 citation