batch_size is forced to 1 when tokenizer. pad_tokeni_id is 0 in huggingface runtime

[pocketbob]

log：

2025-08-19 17:17:51,850 [mlserver][transformer] INFO - Loading model for task 'text-classification'...
2025-08-19 17:17:52,337 [mlserver] WARNING - Model has neither pad_token or eos_token, setting batch size to 1
2025-08-19 17:17:52,755 [mlserver][transformer] WARNING - Model has neither pad_token or eos_token, setting batch size to 1

the id of pad token is 0 in tokenizer_config.json

{
  "added_tokens_decoder": {
    "0": {
      "content": "[PAD]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "100": {
      "content": "[UNK]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "101": {
      "content": "[CLS]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "102": {
      "content": "[SEP]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "103": {
      "content": "[MASK]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "clean_up_tokenization_spaces": true,
  "cls_token": "[CLS]",
  "do_basic_tokenize": true,
  "do_lower_case": true,
  "extra_special_tokens": {},
  "mask_token": "[MASK]",
  "model_max_length": 1000000000000000019884624838656,
  "never_split": null,
  "pad_token": "[PAD]",
  "sep_token": "[SEP]",
  "strip_accents": null,
  "tokenize_chinese_chars": true,
  "tokenizer_class": "BertTokenizer",
  "unk_token": "[UNK]"

line 66 in common.py, if not hf_pipeline.tokenizer.pad_token_id should change to if hf_pipeline.tokenizer.pad_token_id is None

MLServer/runtimes/huggingface/mlserver_huggingface/common.py

Line 66 in 3c9b5dd

if not hf_pipeline.tokenizer.pad_token_id: