Laurent Mazare d9f9c859af Add flash attention (#241) ...

* Add some flash-attn kernel, import the code for flash-attn v2 from Dao-AILab.

* More flash attn.

* Set up the flash attn parameters.

* Get things to compile locally.

* Move the flash attention files in a different directory.

* Build the static C library with nvcc.

* Add more flash attention.

* Update the build part.

* Better caching.

* Exclude flash attention from the default workspace.

* Put flash-attn behind a feature gate.

* Get the flash attn kernel to run.

* Move the flags to a more appropriate place.

* Enable flash attention in llama.

* Use flash attention in llama.

2023-07-26 07:48:10 +01:00

..

convert_checkpoint.py

Resurrect the llama npy support. (#140)

2023-07-11 19:32:10 +01:00

main.rs

Add flash attention (#241)

2023-07-26 07:48:10 +01:00

model.rs

Add flash attention (#241)

2023-07-26 07:48:10 +01:00