Skip to content

Asking about lower NVIDIA GPUs minimum version requirement for CUDA #13545

Answered by mertalev
TAT-Hins asked this question in Q&A
Discussion options

You must be logged in to vote

You can try building ONNX Runtime yourself and setting CMAKE_CUDA_ARCHITECTURES accordingly. Then extend the immich machine learning image, remove the onnxruntime-gpu package, copy over the one you built and install it.

Replies: 1 comment 1 reply

Comment options

You must be logged in to vote
1 reply
@TAT-Hins
Comment options

Answer selected by TAT-Hins
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