conftrace_

draft model

31 papers

Explore in graph

Co-occurring keywords · papers mentioning both

speculative decoding (26) inference acceleration (15) large language model (14) target model (7) inference optimization (5) model compression (4) autoregressive decoding (3) token generation (3) language model (3) model acceleration (2)

Papers

GliDe with a CaPE: A Low-Hassle Method to Accelerate Speculative Decoding ICML 2024 Graph-Structured Speculative Decoding ACL 2024 How Speculative Can Speculative Decoding Be? COLING 2024 Online Speculative Decoding ICML 2024 Speculative Decoding with CTC-based Draft Model for LLM Inference Acceleration NeurIPS 2024 Towards Fast Multilingual LLM Inference: Speculative Decoding and Specialized Drafters EMNLP 2024