Skip to content

How to execute onnxruntime benchmarks through Migraphx ? #2359

Closed Answered by causten
jasberc asked this question in Q&A
Discussion options

You must be logged in to vote

Installing Torch without ROCm can also cause this. i.e. if you ran pip install torch. That version of torch is fully mapped to cuda. You have two options uninstall torch and install via a rocm repo pip install torch==2.0.1 --trusted-host https://repo.radeon.com/ -f https://repo.radeon.com/rocm/manylinux/rocm-rel-5.7/ or use the rocm pytorch docker and install ORT in it... rocm/pytorch:latest

Replies: 1 comment 2 replies

Comment options

You must be logged in to vote
2 replies
@causten
Comment options

Answer selected by jasberc
@jasberc
Comment options

jasberc Oct 26, 2023
Collaborator Author

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Category
Q&A
Labels
None yet
2 participants