Dominik Gyarmati

Lock isn't deleted if task killed by hard-time limit

1

If i set a hard time limit and the task exceeds that limit the task gets killed. But Celery Singleton doesn't delete it, so it keeps it from creating new...

Stabilizer state missing from sLSTM

1

The new sLSTM doesn't have the stabilizer state m. This leads to exploding gradients very easily.

The current problems fixed by this commit: Blocks have a linear layer at the end: `self.proj = nn.Linear(hidden_size, input_size)` Thus leads to an incompatibility, if you use multiple blocks: `xLSTMBlock(embedding_size...

GC policies do not mention how often pruning is done or how it works.

4

### Is this a docs issue? - [X] My issue is about the documentation content or website ### Type of issue I can't find what I'm looking for ### Description...