conftrace_

parallel verification

5 papers

Explore in graph

Co-occurring keywords · papers mentioning both

speculative decoding (5) large language model (2) draft model (2) inference acceleration (2) cpu gpu (1) relaxed acceptance (1) target model (1) dynamic-width beam (1) dynamic window (1) hierarchical decoding (1)

Papers

Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference EMNLP 2025 Dynamic-Width Speculative Beam Decoding for LLM Inference AAAI 2025 Hierarchical Speculative Decoding with Dynamic Window NAACL 2025 Spec-VLA: Speculative Decoding for Vision-Language-Action Models with Relaxed Acceptance EMNLP 2025 How Speculative Can Speculative Decoding Be? COLING 2024