Consider adding prebuild onnx for cpu
#3
by
234r89r23u89023rui90
- opened
Hi,
please consider uploading a prebuild onnx model for cpu inference as well.
I tried to follow the linked tutorial [1], but it requires huge amounts of ram that I do not have access to.
Thank you.
[1] https://github.com/microsoft/onnxruntime-genai/blob/main/examples/python/phi-4-multi-modal.md
We have a pre-built ONNX model for CPU that is already ready to upload. We are waiting for some internal requirements to complete before we can publish it.
234r89r23u89023rui90
changed discussion status to
closed