[Misc] Move utils to avoid conflicts with stdlib, and move tests (#27169)

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

vllm/multimodal/registry.py

@@ -9,7 +9,7 @@ import torch.nn as nn
 from vllm.config.multimodal import BaseDummyOptions
 from vllm.logger import init_logger
 from vllm.transformers_utils.tokenizer import AnyTokenizer, cached_tokenizer_from_config
-from vllm.utils.collections import ClassRegistry
+from vllm.utils.collection_utils import ClassRegistry
 
 from .cache import BaseMultiModalProcessorCache
 from .processing import (

vllm/reasoning/abs_reasoning_parsers.py

@@ -9,7 +9,7 @@ from typing import TYPE_CHECKING, Any
 
 from vllm.entrypoints.tool_server import ToolServer
 from vllm.logger import init_logger
-from vllm.utils.collections import is_list_of
+from vllm.utils.collection_utils import is_list_of
 from vllm.utils.import_utils import import_from_path
 
 if TYPE_CHECKING:

vllm/tracing.py

@@ -5,7 +5,7 @@ import os
 from collections.abc import Mapping
 
 from vllm.logger import init_logger
-from vllm.utils.functools import run_once
+from vllm.utils.func_utils import run_once
 
 TRACE_HEADERS = ["traceparent", "tracestate"]
 

vllm/transformers_utils/processor.py

@@ -16,7 +16,7 @@ from transformers.processing_utils import ProcessorMixin
 from transformers.video_processing_utils import BaseVideoProcessor
 from typing_extensions import TypeVar
 
-from vllm.utils.functools import get_allowed_kwarg_only_overrides
+from vllm.utils.func_utils import get_allowed_kwarg_only_overrides
 
 if TYPE_CHECKING:
     from vllm.config import ModelConfig

vllm/utils/__init__.py

@@ -1122,9 +1122,6 @@ def warn_for_unimplemented_methods(cls: type[T]) -> type[T]:
     return cls
 
 
-## moved to vllm.utils.profiling (imported at module top)
-
-
 # Only relevant for models using ALiBi (e.g, MPT)
 def check_use_alibi(model_config: ModelConfig) -> bool:
     cfg = model_config.hf_text_config
@@ -1150,9 +1147,6 @@ def check_use_alibi(model_config: ModelConfig) -> bool:
     )
 
 
-## moved to vllm.utils.hashing
-
-
 @cache
 def _has_module(module_name: str) -> bool:
     """Return True if *module_name* can be found in the current environment.

vllm/v1/engine/async_llm.py

@@ -30,9 +30,9 @@ from vllm.transformers_utils.config import maybe_register_config_serialize_by_va
 from vllm.transformers_utils.tokenizer import AnyTokenizer, init_tokenizer_from_configs
 from vllm.usage.usage_lib import UsageContext
 from vllm.utils import Device, cdiv
-from vllm.utils.asyncio import cancel_task_threadsafe
-from vllm.utils.collections import as_list
-from vllm.utils.functools import deprecate_kwargs
+from vllm.utils.async_utils import cancel_task_threadsafe
+from vllm.utils.collection_utils import as_list
+from vllm.utils.func_utils import deprecate_kwargs
 from vllm.v1.engine import EngineCoreRequest
 from vllm.v1.engine.core_client import EngineCoreClient
 from vllm.v1.engine.exceptions import EngineDeadError, EngineGenerateError

vllm/v1/engine/core_client.py

@@ -23,7 +23,7 @@ from vllm.config import VllmConfig
 from vllm.logger import init_logger
 from vllm.lora.request import LoRARequest
 from vllm.tasks import SupportedTask
-from vllm.utils.asyncio import in_loop
+from vllm.utils.async_utils import in_loop
 from vllm.utils.network_utils import (
     close_sockets,
     get_open_port,

vllm/v1/worker/gpu_input_batch.py

@@ -13,7 +13,7 @@ from vllm.multimodal.inputs import MultiModalFeatureSpec
 from vllm.pooling_params import PoolingParams
 from vllm.sampling_params import SamplingParams, SamplingType
 from vllm.utils import length_from_prompt_token_ids_or_embeds
-from vllm.utils.collections import swap_dict_values
+from vllm.utils.collection_utils import swap_dict_values
 from vllm.v1.outputs import LogprobsTensors
 from vllm.v1.pool.metadata import PoolingMetadata
 from vllm.v1.sample.logits_processor import (

vllm/v1/worker/tpu_input_batch.py

@@ -10,7 +10,7 @@ import torch
 from vllm.lora.request import LoRARequest
 from vllm.sampling_params import SamplingType
 from vllm.utils import length_from_prompt_token_ids_or_embeds
-from vllm.utils.collections import swap_dict_values
+from vllm.utils.collection_utils import swap_dict_values
 from vllm.v1.outputs import LogprobsTensors
 from vllm.v1.worker.block_table import MultiGroupBlockTable
 from vllm.v1.worker.gpu_input_batch import CachedRequestState