conftrace_

token correction

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

reasoning task (1) large language model (1) contextual sparsity (1) latency reduction (1) inference efficiency (1) language model (1) sparse model (1) model compression (1)

Papers

SIRIUS : Contexual Sparisty with Correction for Efficient LLMs NeurIPS 2024