GPTQ integration (#25062)

* GTPQ integration

* Add tests for gptq

* support for more quantization model

* fix style

* typo

* fix method

* Update src/transformers/modeling_utils.py

Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>

* add dataclass and fix quantization_method

* fix doc

* Update tests/quantization/gptq/test_gptq.py

Co-authored-by: Younes Belkada <49240599+younesbelkada@users.noreply.github.com>

* Apply suggestions from code review

Co-authored-by: Younes Belkada <49240599+younesbelkada@users.noreply.github.com>

* modify dataclass

* add gtpqconfig import

* fix typo

* fix tests

* remove dataset as req arg

* remove tokenizer import

* add offload cpu quantization test

* fix check dataset

* modify dockerfile

* protect trainer

* style

* test for config

* add more log

* overwrite torch_dtype

* draft doc

* modify quantization_config docstring

* fix class name in docstring

* Apply suggestions from code review

Co-authored-by: Younes Belkada <49240599+younesbelkada@users.noreply.github.com>

* more warning

* fix 8bit kwargs tests

* peft compatibility

* remove var

* fix is_gptq_quantized

* remove is_gptq_quantized

* fix wrap

* Update src/transformers/modeling_utils.py

Co-authored-by: Younes Belkada <49240599+younesbelkada@users.noreply.github.com>

* add exllama

* skip test

* overwrite float16

* style

* fix skip test

* Apply suggestions from code review

Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>

* fix docsting formatting

* add doc

* better test

---------

Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>
Co-authored-by: Younes Belkada <49240599+younesbelkada@users.noreply.github.com>

src/transformers/testing_utils.py

@@ -51,6 +51,7 @@ from .integrations import (
 from .utils import (
     is_accelerate_available,
     is_apex_available,
+    is_auto_gptq_available,
     is_bitsandbytes_available,
     is_bs4_available,
     is_cython_available,
@@ -776,6 +777,13 @@ def require_optimum(test_case):
     return unittest.skipUnless(is_optimum_available(), "test requires optimum")(test_case)
 
 
+def require_auto_gptq(test_case):
+    """
+    Decorator for auto_gptq dependency
+    """
+    return unittest.skipUnless(is_auto_gptq_available(), "test requires auto-gptq")(test_case)
+
+
 def require_phonemizer(test_case):
     """
     Decorator marking a test that requires phonemizer