Retrive embeddings from onnxruntime-genai-cuda
#6
by
dkjsnnr1
- opened
Hi There!
Is there any documentation of how to retrive the embeddings generated by the model Phi-3-mini-128k 4int with ONNX runtime using CUDA?
I don't believe there is support for this currently but it is straightforward to add. Can you open a GitHub issue with more details on your scenario?
kvaishnavi
changed discussion status to
closed