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

Inference Latency on VLM decode average

21.1Latency (ms)

W3A16

20.7623.05525.3527.645Dec 27, 2024
Updated 4d ago

Evaluation Results

MethodLinks
2024.12
21.1
2024.12
26.3
2024.12
29.6