DominoTree is a training-free best-first draft tree scored by Domino's path-dependent corrections, delivering higher accepted length and 9–10% overall throughput gains over Domino on Qwen3-4B.
SpecInfer : Accelerating generative large language model serving with tree-based speculative inference and verification
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
DominoTree: Conditional Tree-Structured Drafting with Domino for Speculative Decoding
DominoTree is a training-free best-first draft tree scored by Domino's path-dependent corrections, delivering higher accepted length and 9–10% overall throughput gains over Domino on Qwen3-4B.