M2R2 trains a parallel accelerated residual stream to align with the base model at a faster rate, improving early-exit, self-speculative decoding, and MoE expert prefetching.
Hydra: Sequentially-dependent draft heads for medusa de- coding, 2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
M2R2: Mixture of Multi-Rate Residuals for Efficient Transformer Inference
M2R2 trains a parallel accelerated residual stream to align with the base model at a faster rate, improving early-exit, self-speculative decoding, and MoE expert prefetching.