List your company

LLM Inference Efficiency on Edge Device

43.36Latency (s)RAP
41.755652.585363.41574.2447May 22, 2025

Evaluation results

MethodLinks
RAP2025.0543.3647.23
DENSE2025.0552.439.08
SLICEGPT2025.0564.6431.68
LLM-PRUNER2025.0583.4724.53