Adrian Seyboldt
Adrian Seyboldt
Thanks, that looks great! I think we probably should call `mlx.compile` on the final functions though?
Thanks for reminding me. Sounds like we should add the elemwise logp values as a deterministics (based on an argument to the compilation function). Then we can sort the results...
#74 is related.
@jabrantley You should just be able to compute the elementwise density with this right now: ``` with model: pm.compute_log_likelihood(trace) ``` Or is this not working for you somehow? The issue...
I think with bambi this should do the trick: https://bambinos.github.io/bambi/api/Model.html#bambi.Model.compute_log_likelihood As to an implementation in nutpie itself: We could add an argument `compute_log_likelihood` to `nutpie.compile_pymc_model`. That can pass that info...
No worries :-)
This is really cool and I think it could be useful in a lot of places! With the lazy grads I'm still a little worried that we might break gradient...
There isn't currently any mechanism to call a function for each draw. The progress callback is called once every 50ms or so. I think that might be better for the...
If we want to push progress info to mlflow, I think once every second or so would probably be enough? We don't want to spam the poor thing. I can...
Thanks for reporting. Seems like the python side of the mass matrix storage is broken. The rust code stores the diagonal values and the eigenvalues (not the eigenvectors, which would...