Federico Tomasi

Optimize `_kl_matrix_normal_matrix_normal` for `tfd.MatrixNormalLinearOperator`

1

Hello! I was glad to notice the introduction of the `tfd.MatrixNormal` in 0.13 (even if I saw it a bit late, ie today). However, the implementation of the KL divergence...

**Describe the bug** Vector features are wrongly aggregated by GroupBy operator. **Steps/Code to reproduce bug** ```python import pandas as pd import nvtabular as nvt from nvtabular import ops as nvt_ops...

This is due to the fact that subprocesses on Windows do not inherit the configuration of the logging file handler defined in the father process. Therefore, only logs from the...

Hello! I have been using stable diffusion and adapted few classes to my use case. However I do not understand the step to predict the previous noisy latent variable here:...

simplify e_pri and e_dual computation using squared_norm properties a…

1

…nd remove the use of tuples in place of higher-dimensional np.array

[Q] Possibly unused `self.final_alpha_cumprod`

6

Hello team, quick question to make sure I understand the behavior of the `step` function in LCM Scheduler. https://github.com/huggingface/diffusers/blob/a7361dccdc581147620bbd74a6d295cd92daf616/src/diffusers/schedulers/scheduling_lcm.py#L534-L543 Here, it seems that the condition `prev_timestep >= 0` is always...