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
The sample INT8 API README gives a walkthrough on how to setup the builder for INT8 Neural Network Quantization. Nevertheless, the examples refer to non-existing function calls (e.g setInt8Mode(true)). When following the rest of the example on "Configuring the builder to use INT8 without the INT8 calibrator"
Follow the instructions here on Configuring the builder to use INT8 without the INT8 calibrator and it will not start to quantize to INT8. Especially the call builder->setInt8Mode(true); does not even exist.
The text was updated successfully, but these errors were encountered:
Description
The sample INT8 API README gives a walkthrough on how to setup the builder for INT8 Neural Network Quantization. Nevertheless, the examples refer to non-existing function calls (e.g setInt8Mode(true)). When following the rest of the example on "Configuring the builder to use INT8 without the INT8 calibrator"
Environment
TensorRT Version: 10.0.0
NVIDIA GPU: NVIDIA GeForce RTX 3050 Ti Laptop GPU
NVIDIA Driver Version: 550
CUDA Version: 12.0
CUDNN Version: 8.9.7
Operating System: Ubuntu 22.04 LTS
Python Version (if applicable): -
Tensorflow Version (if applicable): -
PyTorch Version (if applicable): -
Baremetal or Container (if so, version): -
Relevant Files
https://github.com/NVIDIA/TensorRT/tree/28733f0fdccde2967fed395b06ca491af3a561a9/samples/sampleINT8API
Steps To Reproduce
Follow the instructions here on
Configuring the builder to use INT8 without the INT8 calibrator
and it will not start to quantize to INT8. Especially the callbuilder->setInt8Mode(true);
does not even exist.The text was updated successfully, but these errors were encountered: