2022-11-14 14:13:44 +08:00
|
|
|
This CUDA extension implements fused dropout + residual + LayerNorm, based on
|
2022-11-14 13:52:00 +08:00
|
|
|
Apex's [FastLayerNorm](https://github.com/NVIDIA/apex/tree/master/apex/contrib/layer_norm).
|
|
|
|
|
We add dropout and residual, and make it work for both pre-norm and post-norm architecture.
|
2022-11-15 23:10:25 +08:00
|
|
|
|
2022-11-29 09:31:19 +08:00
|
|
|
This only supports a limited set of dimensions, see `csrc/layer_norm/ln_fwd_cuda_kernel.cu`.
|
|
|
|
|
|
2022-11-15 23:10:25 +08:00
|
|
|
It has only been tested on A100s.
|
|
|
|
|
|
2022-11-14 13:52:00 +08:00
|
|
|
```sh
|
|
|
|
|
cd csrc/layer_norm && pip install .
|
|
|
|
|
```
|
