[Bugfix] Replace custom Encoding class with BatchEncoding in MistralTokenizer (#22786)

Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>

vllm/transformers_utils/tokenizers/mistral.py

@@ -2,13 +2,13 @@
 # SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 
 import os
-from dataclasses import dataclass
 from pathlib import Path
 from typing import TYPE_CHECKING, Any, Optional, Union, cast
 
 import huggingface_hub
 import regex as re
 from huggingface_hub import HfApi, hf_hub_download
+from transformers.tokenization_utils_base import BatchEncoding
 
 from vllm.logger import init_logger
 from vllm.transformers_utils.tokenizer_base import TokenizerBase
@@ -27,11 +27,6 @@ if TYPE_CHECKING:
 logger = init_logger(__name__)
 
 
-@dataclass
-class Encoding:
-    input_ids: Union[list[int], list[list[int]]]
-
-
 def maybe_serialize_tool_calls(request: "ChatCompletionRequest"):
     # SEE: https://github.com/vllm-project/vllm/pull/9951
     # Credits go to: @gcalmettes
@@ -359,7 +354,7 @@ class MistralTokenizer(TokenizerBase):
         # For str, single prompt text
         else:
             input_ids = self.encode_one(text, truncation, max_length)
-        return Encoding(input_ids=input_ids)
+        return BatchEncoding({"input_ids": input_ids})
 
     def get_vocab(self) -> dict[str, int]:
         # NB: the dictionary form of the vocabulary collapses token ids that map