conftrace_

lossless acceleration

4 papers

Explore in graph

Co-occurring keywords · papers mentioning both

speculative decoding (4) large language model (3) inference acceleration (3) dynamic draft tree (1) suffix automaton (1) lossless speedup (1) token acceptance rate (1) draft model calibration (1) draft generation (1) hierarchical drafting (1)

Papers

LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification ACL 2026 Lossless Acceleration of Large Language Models with Hierarchical Drafting based on Temporal Locality in Speculative Decoding NAACL 2025 SAM Decoding: Speculative Decoding via Suffix Automaton ACL 2025 EAGLE-2: Faster Inference of Language Models with Dynamic Draft Trees EMNLP 2024