brnguyen2

Results 8 comments of brnguyen2

Request support for Ubuntu24.04

TensorRT 10.8 GA has DEB packages for Ubuntu 24.04: https://developer.nvidia.com/tensorrt/download/10x Closing, please re-open if you are still seeing issues.

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

@david-PHR is this still reproducible on TensorRT 10.8?

Detectron2 - no detections below 832x832 in trt, onnxruntime versions detect correctly

@Huxwell closing this issue - please open a new ticket if this is still an issue on TensorRT 10.8, thanks.

Inference slower on A40 then A30

@decadance-dance can you retry with `nvcr.io/nvidia/tensorrt:25.01-py3` to see if this is still an issue?

[New] Discord channel for triton-inference-server, tensorrt

Hi, you can visit our official Discord sever here for further discussion: https://discord.gg/nvidiadeveloper Thanks!

Engine building failure of TensorRT 10.2.0 (pip install) when building a custom diffusion model on RTX 4090

Closing this ticket; please re-open if this is still an issue on TensorRT 10.8.

I dare you to show me a set of instructions to install and import `tensorrt` on Windows

Hi @doctorpangloss , please provide more detailed reproduction steps explaining the problem. Are you seeing this issue with TensorRT 10.8 Python packages?

Which Visual Studio 2022 BuildTools MSVC is the best version for Cuda 11.8 and Cuda 12.4 and so

Closing as no response since 9/2024