Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

VLM Inference Latency on Jetson Orin llama.cpp quantization

2.89VE Latency (ms/patch)

LLaVA-v1.5-336

2.87282.98893.1053.2211Dec 28, 2023
Updated 3d ago

Evaluation Results

MethodLinks
2023.12
2.899,281367.2617.7419.75
2023.12
2.9422,270474.4930.6612.52
2023.12
2.9824,6551,253.9476.635.9
2023.12
3.1115,678440.638.348.31
2023.12
3.3217,712667.6965.275.14