NVIDIA Developer Forums

How to know Quantization error in TensorRT2.1 for quantized models into INT8/FP16 ?

Accelerated Computing GPU-Accelerated Libraries

adit_bhrgv July 30, 2017, 1:11pm 1

Hello,

Can anyone please let me know if we can calculate or visualize the Quantization error in TensorRT2.1 using half-precision or INT8 quantization ?

Thanks for your help !

Topic		Replies	Views	Activity
Achieving FP32 Accuracy for INT8 Inference Using Quantization Aware Training with NVIDIA TensorRT Technical Blog	1	911	December 3, 2023
[Hugging Face transformer models + pytorch_quantization] PTQ quantization int8 is slower than fp16 TensorRT tensorrt , python , onnx , natural-language-processing-nlp	4	3152	January 6, 2022
Why does Int8 quantization occupy more GPU graphics memory than float16, TensorRT quantization TensorRT	1	638	June 6, 2023
INT8 quantization with Torch-TensorRT fails TensorRT tensorrt , pytorch	3	967	June 29, 2022
TensorRT5/6 FC Layer not support Int8 quantization. TensorRT	4	1029	October 20, 2019
How to quantize a model for Tensorrt? TensorRT tensorrt , pytorch , python	0	192	February 6, 2025
Post-Training Quantization (PTQ) for semantic segmentation model running on Jetson Orin NX Jetson Orin NX tensorrt	24	713	March 26, 2025
Some questions about TensorRT INT8, PTQ and QAT TensorRT tensorrt	5	1943	December 27, 2021
TensorRT quantization uses int8 or uint8 TensorRT tensorrt	1	939	June 6, 2023
QAT int8 TRT engine slower than fp16 TensorRT tensorrt , pytorch , python , onnx	3	2510	January 6, 2022