Yih-Dar 1b3dba9417 Make Gemma work with torch.compile (#30775) ...

* fix

* [run-slow] gemma

* add test

* add `test_compile_static_cache`

* fix

* style

* remove subprocess

* use attribute

* fix

* style

* update

* [run-slow] dbrx,gemma,jetmoe,phi3,recurrent_gemma

---------

Co-authored-by: ydshieh <ydshieh@users.noreply.github.com>

2024-05-16 13:41:33 +02:00

..

__init__.py

[ gemma] Adds support for Gemma 💎 (#29167)

2024-02-21 14:21:28 +01:00

test_modeling_flax_gemma.py

FIX [Gemma / CI] Make sure our runners have access to the model (#29242)

2024-02-28 06:25:23 +01:00

test_modeling_gemma.py

Make Gemma work with torch.compile (#30775)

2024-05-16 13:41:33 +02:00

test_tokenization_gemma.py

[LlamaTokenizerFast] Refactor default llama (#28881)

2024-04-23 23:12:59 +02:00