onnxruntime_backend icon indicating copy to clipboard operation
onnxruntime_backend copied to clipboard

Published 20 hours ago • verified publisher icon triton-inference-server

Don't always calculate all outputs.

Open DavidLangworthy opened this issue 4 years ago • 0 comments
trafficstars

Determine what outputs are needed by the requests in the batch and only calculate those (TF backend contains a representative implementation).

DavidLangworthy avatar Nov 30 '20 14:11 DavidLangworthy