-
Zhengju Tang authored
* [Feature] Add GQA backward kernel with varlen input * [Lint] * [BugFix] Freeze the memory order of all atomic_add operations * [Lint] * [Lint] * [BugFix] Use release order to boost performance
792e5d5b
* [Feature] Add GQA backward kernel with varlen input * [Lint] * [BugFix] Freeze the memory order of all atomic_add operations * [Lint] * [Lint] * [BugFix] Use release order to boost performance