conftrace_

contextual sparsity

4 papers

Explore in graph

Also known as

CS

Co-occurring keywords

large language model (13587) model compression (3302) inference efficiency (248) latency reduction (77) token correction (1) temperature scaling (67) softmax nonlinearity (1) reasoning task (40) efficiency optimization (5) selective self-attention (3)

Papers

SIRIUS : Contexual Sparisty with Correction for Efficient LLMs NIPS 2024
Selective Attention: Enhancing Transformer through Principled Context Control NIPS 2024
ShadowLLM: Predictor-based Contextual Sparsity for Large Language Models EMNLP 2024
Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time ICML 2023