Quantization / TST: Fix remaining quantization tests (#31000)

* Fix remaining quant tests

* Update test_quanto.py

docker/transformers-all-latest-gpu/Dockerfile

@@ -45,9 +45,6 @@ RUN python3 -m pip install --no-cache-dir git+https://github.com/huggingface/opt
 # For video model testing
 RUN python3 -m pip install --no-cache-dir decord av==9.2.0
 
-# For GGUF tests
-RUN python3 -m pip install --no-cache-dir gguf
-
 # Some slow tests require bnb
 RUN python3 -m pip install --no-cache-dir bitsandbytes
 

docker/transformers-quantization-latest-gpu/Dockerfile

@@ -48,6 +48,9 @@ RUN python3 -m pip install --no-cache-dir aqlm[gpu]==1.0.2
 # Add hqq for quantization testing
 RUN python3 -m pip install --no-cache-dir hqq
 
+# For GGUF tests
+RUN python3 -m pip install --no-cache-dir gguf
+
 # Add autoawq for quantization testing
 # >=v0.2.3 needed for compatibility with torch 2.2.1
 RUN python3 -m pip install --no-cache-dir https://github.com/casper-hansen/AutoAWQ/releases/download/v0.2.3/autoawq-0.2.3+cu118-cp38-cp38-linux_x86_64.whl

tests/quantization/quanto_integration/test_quanto.py

@@ -440,14 +440,15 @@ def test_quantize_activation(self):
         self.assertIn("We don't support quantizing the activations with transformers library", str(e.exception))
 
 
+@require_quanto
 @require_torch_gpu
 class QuantoKVCacheQuantizationTest(unittest.TestCase):
     @slow
     @require_read_token
     def test_quantized_cache(self):
         EXPECTED_TEXT_COMPLETION = [
             "Simply put, the theory of relativity states that 1) the speed of light is the same for all observers, and 2) the laws of physics are the same for all observers.\nThe first part of the theory of relativity",
-            "My favorite all time favorite condiment is ketchup. I love it on everything. I love it on my eggs, my fries, my burgers, my hot dogs, my sandwiches, my chicken, my pizza, my sal",
+            "My favorite all time favorite condiment is ketchup. I love it on everything. I love it on my eggs, my fries, my burgers, my hot dogs, my sandwiches, my salads, my chicken, my fish",
         ]
 
         prompts = [