Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Crash for ClassicAra 0.9.5 with Int8 Inference #156

Open
QueensGambit opened this issue Sep 4, 2021 · 0 comments
Open

Crash for ClassicAra 0.9.5 with Int8 Inference #156

QueensGambit opened this issue Sep 4, 2021 · 0 comments
Labels
chess Issue related to chess installation Issues about the installation process int8 inference Issue connected to Int8 neural network inference TensorRT Issues about TensorRT

Comments

@QueensGambit
Copy link
Owner

QueensGambit commented Sep 4, 2021

The ClassicAra 0.9.5 appears to crash when trying to use INT8 inference.
The issue seems to be related to the new ClassicAra model because INT8 still seems to work for CrazyAra 0.9.5.

$ ./ClassicAra
setoption name Precision value int8
info string Updated option Precision to int8
isready
info string onnx file: model/ClassicAra/chess/model-1.19414-0.585-0513-v3.0-bsize-1.onnx
info string no engine file found
info string Building TensorRT engine...
info string This may take a few minutes...
info string run INT8 quantization calibration
The given version '0.3.72' was unexpected and could not be handled

Thanks to Werner Schüle for reporting it.

@QueensGambit QueensGambit added installation Issues about the installation process TensorRT Issues about TensorRT chess Issue related to chess int8 inference Issue connected to Int8 neural network inference labels Sep 4, 2021
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
chess Issue related to chess installation Issues about the installation process int8 inference Issue connected to Int8 neural network inference TensorRT Issues about TensorRT
Projects
None yet
Development

No branches or pull requests

1 participant