works on
eager execution 1large language model training 1memory optimization 1online profiling 1swap-based management 1

From the 1 of 2 linked papers with an AI index.

collaborators
Showing cs.CLShow all

1 paper · 1 filter

cs.CL2026

DART: Diffusion-Inspired Speculative Decoding for Fast LLM Inference

Fuliang Liu, Xue Li, Ketai Zhao +7

Speculative decoding is an effective and lossless approach for accelerating LLM inference. However, existing widely adopted model-based draft designs, such as EAGLE3, improve accur…