onnxruntime
eeec5123 - fix: address review feedback - SafeInt AlignTo, y_bnsh H_v, ORT_ENFORCE

Commit
62 days ago
fix: address review feedback - SafeInt AlignTo, y_bnsh H_v, ORT_ENFORCE - AlignTo now accepts SafeInt<size_t> to maintain overflow protection through alignment arithmetic (fixes SafeInt gap). - y_bnsh_bytes uses H_v (v_head_size) instead of H (head_size) for the Y output buffer to prevent latent under-allocation if v_head_size ever differs from head_size. - Add ORT_ENFORCE(head_size == v_head_size) assertion in UnfusedGqaAttention to make the invariant explicit.
Author
Parents
Loading