rattus ae79e33345 llama: use a more efficient rope implementation (#12434) ...

Get rid of the cat and unary negation and inplace add-cmul the two
halves of the rope. Precompute -sin once at the start of the model
rather than every transformer block.

This is slightly faster on both GPU and CPU bound setups.

2026-02-12 19:56:42 -05:00

35 KiB

Raw Blame History

View Raw