GREATGRAMMA precomputes only the terminal sequences an LLM tokenizer can actually produce, yielding 17.71x faster offline preprocessing than Syncode and 5 to 32 ms online masking per token.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Flexible and Efficient Grammar-Constrained Decoding
GREATGRAMMA precomputes only the terminal sequences an LLM tokenizer can actually produce, yielding 17.71x faster offline preprocessing than Syncode and 5 to 32 ms online masking per token.