TokenTiming uses dynamic time warping on re-encoded token sequences to enable speculative decoding between models with different vocabularies, reporting 1.57x speedup.
Instead, they might be represented by lookup tables or other struc- tures that can grow with the data
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
TokenTiming: A Dynamic Alignment Method for Universal Speculative Decoding Model Pairs
TokenTiming uses dynamic time warping on re-encoded token sequences to enable speculative decoding between models with different vocabularies, reporting 1.57x speedup.