Add scale_diag_mask_inf_softmax operation for transformer attention#15738
Draft
Arya-Hari wants to merge 1 commit intoggml-org:masterfrom
Draft
Add scale_diag_mask_inf_softmax operation for transformer attention#15738Arya-Hari wants to merge 1 commit intoggml-org:masterfrom
Arya-Hari wants to merge 1 commit intoggml-org:masterfrom