[Refactor] TokenizerRegistry only uses lazy imports (#30609)

Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>

tests/tokenizers_/test_basic.py

@@ -3,38 +3,39 @@
 from typing import _get_protocol_attrs  # type: ignore
 
 import pytest
-from transformers import PreTrainedTokenizerBase
+from transformers import (
+    PreTrainedTokenizer,
+    PreTrainedTokenizerBase,
+    PreTrainedTokenizerFast,
+)
 
 from vllm.tokenizers import TokenizerLike, get_tokenizer
+from vllm.tokenizers.mistral import MistralTokenizer
 
 
 def _get_missing_attrs(obj: object, target: type):
     return [k for k in _get_protocol_attrs(target) if not hasattr(obj, k)]
 
 
+def _assert_tokenizer_like(tokenizer: object):
+    missing_attrs = _get_missing_attrs(tokenizer, TokenizerLike)
+    assert not missing_attrs, f"Missing attrs: {missing_attrs}"
+
+
 def test_tokenizer_like_protocol():
-    assert not (
-        missing_attrs := _get_missing_attrs(
-            get_tokenizer("gpt2", use_fast=False),
-            TokenizerLike,
-        )
-    ), f"Missing attrs: {missing_attrs}"
+    tokenizer = get_tokenizer("gpt2", use_fast=False)
+    assert isinstance(tokenizer, PreTrainedTokenizer)
+    _assert_tokenizer_like(tokenizer)
 
-    assert not (
-        missing_attrs := _get_missing_attrs(
-            get_tokenizer("gpt2", use_fast=True),
-            TokenizerLike,
-        )
-    ), f"Missing attrs: {missing_attrs}"
+    tokenizer = get_tokenizer("gpt2", use_fast=True)
+    assert isinstance(tokenizer, PreTrainedTokenizerFast)
+    _assert_tokenizer_like(tokenizer)
 
-    assert not (
-        missing_attrs := _get_missing_attrs(
-            get_tokenizer(
-                "mistralai/Mistral-7B-Instruct-v0.3", tokenizer_mode="mistral"
-            ),
-            TokenizerLike,
-        )
-    ), f"Missing attrs: {missing_attrs}"
+    tokenizer = get_tokenizer(
+        "mistralai/Mistral-7B-Instruct-v0.3", tokenizer_mode="mistral"
+    )
+    assert isinstance(tokenizer, MistralTokenizer)
+    _assert_tokenizer_like(tokenizer)
 
 
 @pytest.mark.parametrize("tokenizer_name", ["facebook/opt-125m", "gpt2"])

tests/tokenizers_/test_registry.py

@@ -2,7 +2,14 @@
 # SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 from pathlib import Path
 
-from vllm.tokenizers import TokenizerLike, TokenizerRegistry, get_tokenizer
+import pytest
+
+from vllm.tokenizers import TokenizerLike
+from vllm.tokenizers.registry import (
+    TokenizerRegistry,
+    get_tokenizer,
+    resolve_tokenizer_args,
+)
 
 
 class TestTokenizer(TokenizerLike):
@@ -40,10 +47,22 @@ class TestTokenizer(TokenizerLike):
         return True
 
 
+@pytest.mark.parametrize("runner_type", ["generate", "pooling"])
+def test_resolve_tokenizer_args_idempotent(runner_type):
+    tokenizer_mode, tokenizer_name, args, kwargs = resolve_tokenizer_args(
+        "facebook/opt-125m",
+        runner_type=runner_type,
+    )
+
+    assert (tokenizer_mode, tokenizer_name, args, kwargs) == resolve_tokenizer_args(
+        tokenizer_name, *args, **kwargs
+    )
+
+
 def test_customized_tokenizer():
     TokenizerRegistry.register("test_tokenizer", __name__, TestTokenizer.__name__)
 
-    tokenizer = TokenizerRegistry.get_tokenizer("test_tokenizer", "abc")
+    tokenizer = TokenizerRegistry.load_tokenizer("test_tokenizer", "abc")
     assert isinstance(tokenizer, TestTokenizer)
     assert tokenizer.path_or_repo_id == "abc"
     assert tokenizer.bos_token_id == 0