mirror of
https://github.com/huggingface/candle.git
synced 2025-06-15 10:26:33 +00:00

* Add the mmv kernels for smaller sizes. * Support more mmv kernels. * Use the new kernels. * Fix the call. * Silly fix. * Improve the testing. * Fix for dmmv. * Add another dedicated test for the batching mmv.
candle-kernels
This crate contains CUDA kernels used from candle. Some of these implementations come from the dfdx crate.