Commit Graph

3 Commits

Author SHA1 Message Date
536c5e702e Cuda kernels for fast min/max reductions (#203)
* Add the min/max cuda kernels.

* Better integration of the cuda kernels.
2023-07-19 18:12:27 +01:00
ec79fc43f2 Add the bf16 cuda kernels. 2023-06-29 23:12:02 +01:00
d7f729fb8f Refactor the hierarchy. 2023-06-27 11:57:27 +02:00