focusunsink

Results 13 comments of focusunsink

I faced with the same problem, but my netowork is fine. I can access google .

# for i in range(network.num_layers): # layer = network.get_layer(i) # if 'norm' in layer.name: # print("this is a layernorm", layer.type, layer.name, layer.precision) # #layer.precision = trt.DataType.FLOAT # elif layer.type ==...

![image](https://github.com/user-attachments/assets/a7723b78-f36e-4527-b4af-2914369af166) this is my docker image , is there any suggestion for the version of docker image.

Thansk you KevinHush, After Update docker image to dev version insteam of dev-slim. I got this. ` [WARNING] [2024-10-11 16:02:00,124] [synonym.__init__] [line:40]: Realtime synonym is disabled, since no redis connection....

maybe I faced the same problem when I use my fp8 model

I solved this problem myself. Even nvidia-smi shows cuda version is 12.4, nvcc version is 12.1. The hopper/setup.py will check nvcc version, so this error occured. After upgrading nvcc verion...

GPU: 4090 or H800. tensorrt 10.6.0 torch 2.4.0 when I compile unet using tensorrt. it raise this error. Even I use H800 to make more memory available. This error still...

This is because image is to large or frames is too many. when I change frames from 72 to 16. it success.