Your language model forgets everything. Sillage gives it a 4 MB memory that persists across sessions, no gradients, no fine-tuning, no growing index. Beats an unbounded kNN-LM at 1/13 the storage (perplexity 31 → 17). CPU-only, fully reproducible, four preprints with Zenodo DOIs.
A modular and easy-to-use framework for Test-Time Training (TTT) and Test-Time Adaptation (TTA) in Pytorch, making your networks more generalizable with minimal effort ✨
