In the documentation here: Bring your own model (BYOM) - Edge Impulse Documentation it says that you can upload an npy file to have the model be quantized when uploading a pre-built model. However i do not see this option when uploading my custom tflite model.
I see what you mean, I think this is because the npy array is optional and to be included in the saved_model.zip, but will need to check.
We are in contact on email so lets just update here once that discussion with sales and solutions is complete, as you have a number of other topics they will need to go through with you.
1. Upload your trained model
Upload a TensorFlow SavedModel (saved_model.zip), ONNX model (.onnx), TensorFlow Lite model (.tflite), LGBM model (.txt), XGBoost model (.json) or pickle model (.pkl) to get started.
Best
Eoin