Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Visual-Language Model Inference on VILA RTX 4090

168.1Throughput (tokens/sec)

VILA-7B-AWQ

54.11683.708113.3142.892Jun 1, 2023
Updated 2mo ago

Evaluation Results

MethodLinks
2023.06
168.1
2023.06
99
2023.06
58.5