error 126 Onnx in ComfyUI[Performance] O

[Kev2408]

Describe the issue

can you help me with this, i don t have a clue

To reproduce

xx

Urgency

very slow processing of workflows

Platform

Windows

OS Version

11

ONNX Runtime Installation

Built from Source

ONNX Runtime Version or Commit ID

latest

ONNX Runtime API

Python

Architecture

X64

Execution Provider

CUDA

Execution Provider Library Version

12.3 CUDA

[skottmckay]

You need to make sure all the required CUDA and cuDNN dlls can be found. One way is for the PATH environment variable to have entries for the CUDA/cuDNN paths.

https://learn.microsoft.com/en-us/windows/win32/dlls/dynamic-link-library-search-order

Make sure you follow the documentation for the specific version of cuDNN you're using as the instructions may differ (e.g. whether zlib needs to be installed or not has changed).

https://docs.nvidia.com/deeplearning/cudnn/archives/index.html