[Minor] Delete Llama tokenizer warnings (#2146)

Author: WoosukKwon

vllm/transformers_utils/tokenizer.py

@@ -8,9 +8,6 @@
 
 logger = init_logger(__name__)
 
-# A fast LLaMA tokenizer with the pre-processed `tokenizer.json` file.
-_FAST_LLAMA_TOKENIZER = "hf-internal-testing/llama-tokenizer"
-
 
 def get_tokenizer(
     tokenizer_name: str,
@@ -27,27 +24,13 @@ def get_tokenizer(
                 "Cannot use the fast tokenizer in slow tokenizer mode.")
         kwargs["use_fast"] = False
 
-    if ("llama" in tokenizer_name.lower() and kwargs.get("use_fast", True)
-            and tokenizer_name != _FAST_LLAMA_TOKENIZER):
-        logger.info(
-            "For some LLaMA V1 models, initializing the fast tokenizer may "
-            "take a long time. To reduce the initialization time, consider "
-            f"using '{_FAST_LLAMA_TOKENIZER}' instead of the original "
-            "tokenizer.")
     try:
         tokenizer = AutoTokenizer.from_pretrained(
             tokenizer_name,
             *args,
             trust_remote_code=trust_remote_code,
             tokenizer_revision=tokenizer_revision,
             **kwargs)
-    except TypeError as e:
-        # The LLaMA tokenizer causes a protobuf error in some environments.
-        err_msg = (
-            "Failed to load the tokenizer. If you are using a LLaMA V1 model "
-            f"consider using '{_FAST_LLAMA_TOKENIZER}' instead of the "
-            "original tokenizer.")
-        raise RuntimeError(err_msg) from e
     except ValueError as e:
         # If the error pertains to the tokenizer class not existing or not
         # currently being imported, suggest using the --trust-remote-code flag.