0 0 1 C++

Fix more int overflow during quant (PPL/CUDA). (#6563)

* Fix more int overflow during quant.

* Fix some more int overflow in softmax.

* Revert back to int64_t.

DAN™ committed 2y ago

e00b4a8f816ebc45b98a46e5f5231359b9a017e0

Parent: 7bb36cc

Committed by GitHub <noreply@github.com> on 4/28/2024, 10:38:44 PM