[Inference] Support the logic related to ignoring EOS token (#5693)

* Adapt temperature processing logic

* add ValueError for top_p and top_k

* add GQA Test

* fix except_msg

* support ignore EOS token

* change variable's name

* fix annotation

colossalai/inference/core/engine.py

@@ -662,6 +662,7 @@ class InferenceEngine:
                 self.tokenizer.eos_token_id,
                 self.tokenizer.pad_token_id,
                 max_output_len=max_new_tokens,
+                ignore_eos=self.inference_config.ignore_eos,
             )
             self.request_handler.add_sequence(sequence)