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

From the 1 of 16 linked papers with an AI index.

collaborators
Showing cs.OSShow all

1 paper · 1 filter

cs.OS2026

SSV: Sparse Speculative Verification for Efficient LLM Inference

Zhibin Wang, Ziyu Zhong, Nuo Shen +3

Speculative decoding and dynamic sparse attention are two complementary approaches for accelerating long-context LLM inference: the former amortizes target-model execution across m…