Something changed in `pytensor > 2.12.3` (and thus `pymc > 5.6.1`) that makes my `pytensor.gradient.grad` call get stuck - any ideas?

Questions v5
29

Just heading out the door, thanks for the quick reply!

mdl.initial_point
returns:

{'m_mu': array([0., 0.]),
 'm_s_log__': array([0., 0.]),
 'lkjcc_cholesky-cov-packed__': array([0., 0., 0.])}

…which might be a good thing?

Also I dont yet know how to use mdl.replace_rvs_by_values(), but a first guess mdl.replace_rvs_by_values(y_c) errors out:

TypeError: TensorType does not support iteration.
	Did you pass a PyTensor variable to a function that expects a list?
	Maybe you are using builtins.sum instead of pytensor.tensor.sum?