🚨🚨 Fix beam score calculation issue for decoder-only models (#27351)

* Fix beam score calculation issue for decoder-only models

* Update beam search test and fix code quality issue

* Fix beam_sample, group_beam_search and constrained_beam_search

* Split test for pytorch and TF, add documentation

---------

Co-authored-by: Xin Qiu <xin.qiu@sentient.ai>

tests/generation/test_framework_agnostic.py

@@ -633,7 +633,11 @@ class GenerationIntegrationTestsMixin:
             "do_sample": False,
             "num_beams": 3,
         }
-        expectation = 13
+        if is_pt:
+            expectation = 20
+        else:
+            # TODO (joao): fix me
+            expectation = 13
 
         tokenizer = AutoTokenizer.from_pretrained("hf-internal-testing/tiny-random-gpt2")
         text = """Hello, my dog is cute and"""