turboderp f79e16c5d0 Optimization, wider loads in EXL2 kernel (int4)

2023-09-07 10:56:43 +02:00

..

chat.py

Fix bug in 6-bit matrix preproc

2023-09-06 08:47:09 +02:00

inference.py

Optimization, wider loads in EXL2 kernel (int4)

2023-09-07 10:56:43 +02:00

streaming.py

Tidying up

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