openvino

23a7e4e1 - [CPU] Fix SDPA node attention mask precision handling for bf16/f16 inference (#33132)

[CPU] Fix SDPA node attention mask precision handling for bf16/f16 inference (#33132) ### Details: - *Use actual attention mask input precision instead of compute precision (bf16/f16) to fix LFM2-350M output corruption when running with low precision on Xeon platforms.* ### Tickets: - *CVS-177340*