conftrace_

token acceptance

4 papers

Explore in graph

Co-occurring keywords · papers mentioning both

speculative decoding (4) large language model (3) inference optimization (2) hybrid drafting (1) batch inference (1) dynamic length policy (1) language model inference (1) model acceleration (1) draft model (1) inference acceleration (1)

Papers

Steering Pretrained Drafters During Speculative Decoding AAAI 2026 Talon: Breaking the Synchronization Barrier in Speculative Decoding with Hybrid Model-based and Retrieve-based Drafting AAAI 2026 Draft Model Knows When to Stop: Self-Verification Speculative Decoding for Long-Form Generation EMNLP 2025 TETRIS: Optimal Draft Token Selection for Batch Speculative Decoding ACL 2025