Slow inference time
Opened this issue · 0 comments
ahndroo commented
When running the model on my RTX6000 ADA, the inference time is near 200ms for a batch of 1. What would cause such a large deviation from the reported 55ms on an RTX3090?
Opened this issue · 0 comments
When running the model on my RTX6000 ADA, the inference time is near 200ms for a batch of 1. What would cause such a large deviation from the reported 55ms on an RTX3090?