Hello there,I was recently developing and model which is required to use some LSTM layers. I found that in deed Ethos-U65 is supporting LSTM: https://developer.arm.com/documentation/102023/0000/Programmers-model/Operators-and-performance/Supported-data-types-and-operators.
I stumble upon a fact that with most of the frameworks it is hard to quantize those layers as their performance is poor (after PTQ). Can you suggest what is the right path for LSTM layer integration with NPU? Maybe use of dynamic quantization?Thank you,Tymo
Using Ethos-U65 for LSTM layers can be tricky, especially when dealing with post-training quantization. Dynamic quantization often helps maintain accuracy while leveraging NPU acceleration. Optimizing layer sizes and sequence lengths can also improve performance on embedded NPUs.