Fixed LSTM

[veblush]

This PR fixes two critical issues in arm_lstm_unidirectional_s8 and s16 that prevent state persistence in streaming models and cause out-of-bounds reads during non-time-major inference. These issues are closely related to in tensorflow/tflite-micro#3564.

Problem:

• State Wiping: By default, arm_lstm_unidirectional_* unconditionally sets hidden_in to NULL and memsets cell_state to 0. This discards the HiddenStateTensor and CellStateTensor that TFLM relies on to persist state across Invoke() calls for streaming models.
• Striding Bug: In the time_major = false block of arm_lstm_unidirectional_*, CMSIS-NN attempts to jump between batches by passing batch_offset = params->time_steps to arm_nn_lstm_step_*. However, arm_nn_lstm_step_* forwards this batch_offset to arm_nn_vec_mat_mul_result_acc_s8_s16 for both the data_in and hidden_in pointers. Since the hidden_state buffer is contiguous (stride 1) and not strided like data_in, passing batch_offset = params->time_steps causes out-of-bounds reads on the hidden_in buffer at timestep t=0.

Solution:

• Adding a hidden_state pointer to cmsis_nn_lstm_context.
• Forwarding this hidden_state as hidden_in when present, skipping the cell_state wiping if so.
• Explicitly iterating over the batch_size in the time_major = false case when computing step sizes, which forces batch_offset = 1 and avoids the buggy out-of-bounds stride entirely while writing to the final memory buffer sequentially.

[mansnils]

Thank you Esun!
The PR looks good! Could you add a unit test?
I think this condition - time_major=false && batch > 1 && time_steps > 1 - should catch it?

Please update date/revisions. That would be the patch version to update.