jgrusewski 9c7300412a fix(ml): Fix quantized attention dropout compatibility ...

- Add .t() transpose to all weight matrix multiplications
- Add .contiguous() after transpose to fix non-contiguous errors
- Fix causal mask using additive masking instead of where_cond
- Fix mask dtype compatibility (F32 instead of U8)

All 8 quantized_attention tests now passing.

2025-10-23 11:40:01 +02:00

7.3 KiB

Raw Blame History

View Raw