You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I tested the inference runtime on a model with ONNX runtime and with the Triton Inference Server and with Triton the runtime was around 50% higher than with ONNX.
Now I did some research and saw that shared memory regions should be the solution to getter better runtime performance in Triton, however they are (understandably) not available on Windows.
So I assume there is no way to get native runtime performance with the Triton Inference Server on Windows, or am I missing something?
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
Hi Everyone,
I tested the inference runtime on a model with ONNX runtime and with the Triton Inference Server and with Triton the runtime was around 50% higher than with ONNX.
Now I did some research and saw that shared memory regions should be the solution to getter better runtime performance in Triton, however they are (understandably) not available on Windows.
So I assume there is no way to get native runtime performance with the Triton Inference Server on Windows, or am I missing something?
Kind regards,
Johannes
Beta Was this translation helpful? Give feedback.
All reactions