Issue #10: Kernel Fusion using torch.jit

From the issue description:

Fuse some popular functions and automatically replace modules in an existing 🤗 transformers model with their corresponding fusion module

TODOs

[x] Decide on location to implement fused functions
[x] Decide on a way to automatically replace modules on import, i.e. whenever someone imports a 🤗transformer model, its activations are replaced with the fused implementations. @xrsrke I'm not sure I understand this part properly?
[x] Fuse bias addition and GeLU [link]
[x] Fuse bias addition and dropout [link]
[x] Error-check dropout code at first glance to make sure forward/backward passes are correct
[x] Write unit tests for fusion layers
- For some reason, the torch Dropout is zeroing out several more things in the unit test
- The Fused Gelu is asking me for a static forward method, which is already implemented, so not sure what's going on there
[ ] Write test for toy model
- Relatively inexperienced here, so might need a hand

Reading (could be ignored)

xrsrke / pipegoose