turboderp 6d576b3e56 Reworking attention, allow for batched inference with independent cache per sequence

2023-09-03 15:56:38 +02:00

..

chat.py

Initial commit

2023-08-30 11:05:23 +02:00

inference.py

Reworking attention, allow for batched inference with independent cache per sequence

2023-09-03 15:56:38 +02:00

streaming.py

Tidying up

2023-09-02 16:40:57 +02:00