[Chore] Rename `utils` submodules (#26920)

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

tests/lora/test_add_lora.py

@@ -12,7 +12,7 @@ from vllm.entrypoints.openai.api_server import (
 from vllm.inputs import TextPrompt
 from vllm.lora.request import LoRARequest
 from vllm.sampling_params import SamplingParams
-from vllm.utils.async_utils import merge_async_iterators
+from vllm.utils.asyncio import merge_async_iterators
 
 MODEL_PATH = "zai-org/chatglm3-6b"
 LORA_RANK = 64

tests/models/multimodal/generation/test_common.py

@@ -17,7 +17,7 @@ from transformers import (
 )
 
 from vllm.platforms import current_platform
-from vllm.utils.func import identity
+from vllm.utils.functools import identity
 
 from ....conftest import (
     IMAGE_ASSETS,

tests/utils_/test_async_utils.py

@@ -5,7 +5,7 @@ from collections.abc import AsyncIterator
 
 import pytest
 
-from vllm.utils.async_utils import merge_async_iterators
+from vllm.utils.asyncio import merge_async_iterators
 
 
 async def _mock_async_iterator(idx: int):

tests/utils_/test_func_utils.py

@@ -4,7 +4,7 @@
 
 import pytest
 
-from vllm.utils.func import deprecate_kwargs, supports_kw
+from vllm.utils.functools import deprecate_kwargs, supports_kw
 
 from ..utils import error_on_warning
 

vllm/benchmarks/throughput.py

@@ -34,7 +34,7 @@ from vllm.inputs import TextPrompt, TokensPrompt
 from vllm.lora.request import LoRARequest
 from vllm.outputs import RequestOutput
 from vllm.sampling_params import BeamSearchParams
-from vllm.utils.async_utils import merge_async_iterators
+from vllm.utils.asyncio import merge_async_iterators
 
 
 def run_vllm(

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.func import supports_kw
+from vllm.utils.functools import supports_kw
 
 logger = init_logger(__name__)
 

vllm/entrypoints/openai/serving_completion.py

@@ -35,7 +35,7 @@ from vllm.outputs import RequestOutput
 from vllm.sampling_params import BeamSearchParams, SamplingParams
 from vllm.transformers_utils.tokenizer import AnyTokenizer
 from vllm.utils import as_list
-from vllm.utils.async_utils import merge_async_iterators
+from vllm.utils.asyncio import merge_async_iterators
 
 logger = init_logger(__name__)
 

vllm/entrypoints/openai/serving_embedding.py

@@ -40,7 +40,7 @@ from vllm.outputs import (
 )
 from vllm.pooling_params import PoolingParams
 from vllm.utils import chunk_list
-from vllm.utils.async_utils import merge_async_iterators
+from vllm.utils.asyncio import merge_async_iterators
 
 logger = init_logger(__name__)
 

vllm/entrypoints/openai/serving_engine.py

@@ -91,7 +91,7 @@ from vllm.tracing import (
 )
 from vllm.transformers_utils.tokenizer import AnyTokenizer, MistralTokenizer
 from vllm.utils import is_list_of, random_uuid
-from vllm.utils.async_utils import (
+from vllm.utils.asyncio import (
     AsyncMicrobatchTokenizer,
     collect_from_async_generator,
     make_async,

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.async_utils import merge_async_iterators
+from vllm.utils.asyncio 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.async_utils import make_async, merge_async_iterators
+from vllm.utils.asyncio import make_async, merge_async_iterators
 
 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.async_utils import AsyncMicrobatchTokenizer
+from vllm.utils.asyncio import AsyncMicrobatchTokenizer
 
 
 @dataclass(frozen=True)

vllm/executor/executor_base.py

@@ -17,7 +17,7 @@ from vllm.logger import init_logger
 from vllm.lora.request import LoRARequest
 from vllm.sequence import ExecuteModelRequest
 from vllm.tasks import SupportedTask
-from vllm.utils.async_utils import make_async
+from vllm.utils.asyncio import make_async
 from vllm.v1.outputs import SamplerOutput
 from vllm.v1.worker.worker_base import WorkerBase
 

vllm/executor/ray_distributed_executor.py

@@ -24,7 +24,7 @@ from vllm.utils import (
     get_ip,
     get_open_port,
 )
-from vllm.utils.async_utils import make_async
+from vllm.utils.asyncio import make_async
 from vllm.v1.outputs import SamplerOutput
 
 if ray is not None:

vllm/model_executor/layers/fused_moe/deep_gemm_moe.py

@@ -29,7 +29,7 @@ from vllm.model_executor.layers.quantization.utils.fp8_utils import (
 )
 from vllm.utils import has_deep_gemm
 from vllm.utils.deep_gemm import m_grouped_fp8_gemm_nt_contiguous
-from vllm.utils.func import run_once
+from vllm.utils.functools import run_once
 
 logger = init_logger(__name__)
 

vllm/model_executor/models/interfaces.py

@@ -24,7 +24,7 @@ from vllm.inputs import TokensPrompt
 from vllm.inputs.data import PromptType
 from vllm.logger import init_logger
 from vllm.model_executor.layers.quantization import QuantizationConfig
-from vllm.utils.func import supports_kw
+from vllm.utils.functools import supports_kw
 
 from .interfaces_base import VllmModel, is_pooling_model
 

vllm/model_executor/models/interfaces_base.py

@@ -15,7 +15,7 @@ import torch.nn as nn
 from typing_extensions import TypeIs, TypeVar
 
 from vllm.logger import init_logger
-from vllm.utils.func import supports_kw
+from vllm.utils.functools import supports_kw
 
 if TYPE_CHECKING:
     from vllm.config import VllmConfig

vllm/multimodal/processing.py

@@ -26,7 +26,7 @@ from vllm.logger import init_logger
 from vllm.transformers_utils.processor import cached_processor_from_config
 from vllm.transformers_utils.tokenizer import AnyTokenizer, decode_tokens, encode_tokens
 from vllm.utils import flatten_2d_lists, full_groupby
-from vllm.utils.func import get_allowed_kwarg_only_overrides
+from vllm.utils.functools import get_allowed_kwarg_only_overrides
 from vllm.utils.jsontree import JSONTree, json_map_leaves
 
 from .hasher import MultiModalHasher

vllm/tracing.py

@@ -5,7 +5,7 @@ import os
 from collections.abc import Mapping
 
 from vllm.logger import init_logger
-from vllm.utils.func import run_once
+from vllm.utils.functools 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.func import get_allowed_kwarg_only_overrides
+from vllm.utils.functools import get_allowed_kwarg_only_overrides
 
 if TYPE_CHECKING:
     from vllm.config import ModelConfig