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

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

vllm/entrypoints/chat_utils.py

@@ -51,7 +51,7 @@ from vllm.transformers_utils.chat_templates import get_chat_template_fallback_pa
 from vllm.transformers_utils.processor import cached_get_processor
 from vllm.transformers_utils.tokenizer import AnyTokenizer, MistralTokenizer
 from vllm.utils import random_uuid
-from vllm.utils.functools import supports_kw
+from vllm.utils.func_utils import supports_kw
 
 logger = init_logger(__name__)
 

vllm/entrypoints/llm.py

@@ -76,7 +76,7 @@ from vllm.transformers_utils.tokenizer import (
 )
 from vllm.usage.usage_lib import UsageContext
 from vllm.utils import Counter, Device
-from vllm.utils.collections import as_iter, is_list_of
+from vllm.utils.collection_utils import as_iter, is_list_of
 from vllm.v1.engine import EngineCoreRequest
 from vllm.v1.engine.llm_engine import LLMEngine
 from vllm.v1.sample.logits_processor import LogitsProcessor

vllm/entrypoints/openai/serving_chat.py

@@ -70,7 +70,7 @@ from vllm.transformers_utils.tokenizers import (
     truncate_tool_call_ids,
     validate_request_params,
 )
-from vllm.utils.collections import as_list
+from vllm.utils.collection_utils import as_list
 
 logger = init_logger(__name__)
 

vllm/entrypoints/openai/serving_completion.py

@@ -34,8 +34,8 @@ from vllm.logprobs import Logprob
 from vllm.outputs import RequestOutput
 from vllm.sampling_params import BeamSearchParams, SamplingParams
 from vllm.transformers_utils.tokenizer import AnyTokenizer
-from vllm.utils.asyncio import merge_async_iterators
-from vllm.utils.collections import as_list
+from vllm.utils.async_utils import merge_async_iterators
+from vllm.utils.collection_utils import as_list
 
 logger = init_logger(__name__)
 

vllm/entrypoints/openai/serving_embedding.py

@@ -39,8 +39,8 @@ from vllm.outputs import (
     RequestOutput,
 )
 from vllm.pooling_params import PoolingParams
-from vllm.utils.asyncio import merge_async_iterators
-from vllm.utils.collections import chunk_list
+from vllm.utils.async_utils import merge_async_iterators
+from vllm.utils.collection_utils import chunk_list
 
 logger = init_logger(__name__)
 

vllm/entrypoints/openai/serving_engine.py

@@ -91,13 +91,13 @@ from vllm.tracing import (
 )
 from vllm.transformers_utils.tokenizer import AnyTokenizer, MistralTokenizer
 from vllm.utils import random_uuid
-from vllm.utils.asyncio import (
+from vllm.utils.async_utils import (
     AsyncMicrobatchTokenizer,
     collect_from_async_generator,
     make_async,
     merge_async_iterators,
 )
-from vllm.utils.collections import is_list_of
+from vllm.utils.collection_utils import is_list_of
 from vllm.v1.engine import EngineCoreRequest
 
 logger = init_logger(__name__)

vllm/entrypoints/openai/serving_pooling.py

@@ -36,7 +36,7 @@ from vllm.entrypoints.utils import _validate_truncation_size
 from vllm.logger import init_logger
 from vllm.outputs import PoolingOutput, PoolingRequestOutput
 from vllm.tasks import SupportedTask
-from vllm.utils.asyncio import merge_async_iterators
+from vllm.utils.async_utils import merge_async_iterators
 
 logger = init_logger(__name__)
 

vllm/entrypoints/openai/serving_score.py

@@ -37,7 +37,7 @@ from vllm.logger import init_logger
 from vllm.lora.request import LoRARequest
 from vllm.outputs import PoolingRequestOutput, ScoringRequestOutput
 from vllm.transformers_utils.tokenizer import AnyTokenizer, MistralTokenizer
-from vllm.utils.asyncio import make_async, merge_async_iterators
+from vllm.utils.async_utils import make_async, merge_async_iterators
 
 logger = init_logger(__name__)
 

vllm/entrypoints/openai/tool_parsers/abstract_tool_parser.py

@@ -12,7 +12,7 @@ from vllm.entrypoints.openai.protocol import (
 )
 from vllm.logger import init_logger
 from vllm.transformers_utils.tokenizer import AnyTokenizer
-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
 
 logger = init_logger(__name__)

vllm/entrypoints/renderer.py

@@ -17,7 +17,7 @@ from vllm.inputs.data import TextPrompt as EngineTextPrompt
 from vllm.inputs.data import TokensPrompt as EngineTokensPrompt
 from vllm.inputs.parse import get_prompt_components, parse_raw_prompts
 from vllm.transformers_utils.tokenizer import AnyTokenizer
-from vllm.utils.asyncio import AsyncMicrobatchTokenizer
+from vllm.utils.async_utils import AsyncMicrobatchTokenizer
 
 
 @dataclass(frozen=True)