darknight054 a47c7e4ba9 Reduce KV cache memory (#51) ...

Hi! This PR tackles the memory issues discussed in [Reduce Memory
Usage](https://github.com/kyutai-labs/pocket-tts/issues/14) by removing
the "always allocate 1000 steps" KV-cache behavior.

2026-02-03 12:32:46 +01:00

..

__init__.py

Copy the files in the new repo for public release

2026-01-12 11:25:16 +01:00

flow_lm.py

Pin the versions of the files we're using and allow offline use (#27)

2026-01-14 12:55:38 +01:00

mimi.py

Copy the files in the new repo for public release

2026-01-12 11:25:16 +01:00

tts_model.py

Reduce KV cache memory (#51)

2026-02-03 12:32:46 +01:00