pijddlmZddlZdgZGddejj j jZy))AnyNLSTMceZdZdZej j jjZ de fdZ e de de ddfdZe dedd ej j jjddfd Zy) rarA quantized long short-term memory (LSTM). For the description and the argument types, please, refer to :class:`~torch.nn.LSTM` Attributes: layers : instances of the `_LSTMLayer` .. note:: To access the weights and biases, you need to access them per layer. See examples in :class:`~torch.ao.nn.quantizable.LSTM` Examples:: >>> # xdoctest: +SKIP >>> custom_module_config = { ... 'float_to_observed_custom_module_class': { ... nn.LSTM: nn.quantizable.LSTM, ... }, ... 'observed_to_quantized_custom_module_class': { ... nn.quantizable.LSTM: nn.quantized.LSTM, ... } ... } >>> tq.prepare(model, prepare_custom_module_class=custom_module_config) >>> tq.convert(model, convert_custom_module_class=custom_module_config) returncy)N QuantizedLSTM)selfs c/opt/services/ai/voice_agent/venv/lib/python3.12/site-packages/torch/ao/nn/quantized/modules/rnn.py _get_namezLSTM._get_name'sargskwargsNctd)NzrIt looks like you are trying to convert a non-observed LSTM module. Please, see the examples on quantizable LSTMs.)NotImplementedError)clsrrs r from_floatzLSTM.from_float*s" 1  r rotherct||jsJtjjj |dd}||_|S)NFT)inplaceremove_qconfig) isinstance _FLOAT_MODULEtorchao quantizationconvert __class__)rr converteds r from_observedzLSTM.from_observed4sN%!2!2333HH))11 52 " r )__name__ __module__ __qualname____doc__rrnn quantizablerrstrr classmethodrrtyper r r r rr s2HHKK++00M3 s c d  4< 0G0G0L0LQWr )typingrr__all__rr%r&rr r r r,s7    0588;; " " ' '0r