Description When I optimize the same model with tensorRT_optimization tool on Nvidia Drive AGX platform twice in a row , I get two binary files of different sizes. Also, it is mentioned here GitHub - NVIDIA/framework-determinism: Providing determinism in deep learning frameworks that TensorRT behav…

Hi @domagoj.krivosic , [image] domagoj.krivosic: If we optimize the same model (with the same parameters - weights) twice, should we expect to get exactly the same engine files? If not, is it possible to achieve this reproducibility? The below link will help you answer your query De…

Deterministic TensorRT optimization

AI & Data Science Deep Learning (Training & Inference) TensorRT

AakankshaS August 26, 2020, 5:41pm 6

Hi @domagoj.krivosic,

The below link will help you answer your query

Thanks!

Topic		Replies	Views
Non-deterministic TensorRT engine building TensorRT tensorrt	3	585	March 10, 2021
Trtexec generates different engines when using the same platform/machine with the same onnx model TensorRT	3	1178	March 29, 2022
Is TensorRT inference deterministic/reproducibile? TensorRT tensorrt	5	2678	October 12, 2021
Question about TensorRT reproducibility on different architectures TensorRT	3	927	October 12, 2021
Is TensorRT “floating-point 16 precision mode” non-deterministic on Jetson TX2? Jetson TX2	6	1398	October 18, 2021
Two TRT compiled engines that were generated from the same Onnx model show different inference average times TensorRT cudnn	2	156	August 11, 2024
Run to run variation with TensorRT TensorRT tensorrt	1	404	September 2, 2022
TensorRT and Triton Server - different results each time TensorRT	2	503	October 12, 2021
TensorRT and Triton Server - different results each time Triton Inference Server (archived)	0	810	May 31, 2021
TensorRT Plan Building Deterministic TensorRT	1	400	November 27, 2019

Deterministic TensorRT optimization

Related topics