David

Resize when Antialias=True seems not working

7

## Description Compiling a TensorRT model from an ONNX IR containing Resize operators with Antialias=1 does not apply the antialiasing. Does antialias is supported in the TensorRT resize operator? ##...

Custom Attention implementation not well optimised by TensorRT

12

## Description Hi, I am working on a model that employs a modified attention mechanism, incorporating pooling on top of K and V to reduce computational load. However, I'm encountering...

TensorRT 10 slower than TensorRT 8.6 for models with Instance Normalization layers

4

## Description After migrating my backend to TensorRT 10, I've noticed that some models are slower with TensorRT-10. Looks like the issue comes from the mapping on some InstanceNormalization layers...