[Misc] Move utils to avoid conflicts with stdlib, and move tests (#27169)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
@@ -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.asyncio import merge_async_iterators
|
||||
from vllm.utils.async_utils import merge_async_iterators
|
||||
|
||||
|
||||
def run_vllm(
|
||||
|
||||
@@ -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__)
|
||||
|
||||
|
||||
@@ -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
|
||||
|
||||
@@ -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__)
|
||||
|
||||
|
||||
@@ -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__)
|
||||
|
||||
|
||||
@@ -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__)
|
||||
|
||||
|
||||
@@ -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__)
|
||||
|
||||
@@ -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__)
|
||||
|
||||
|
||||
@@ -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__)
|
||||
|
||||
|
||||
@@ -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__)
|
||||
|
||||
@@ -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)
|
||||
|
||||
@@ -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.asyncio import make_async
|
||||
from vllm.utils.async_utils import make_async
|
||||
from vllm.v1.outputs import SamplerOutput
|
||||
from vllm.v1.worker.worker_base import WorkerBase
|
||||
|
||||
|
||||
@@ -19,7 +19,7 @@ from vllm.logger import init_logger
|
||||
from vllm.platforms import current_platform
|
||||
from vllm.ray.ray_env import get_env_vars_to_copy
|
||||
from vllm.sequence import ExecuteModelRequest
|
||||
from vllm.utils.asyncio import make_async
|
||||
from vllm.utils.async_utils import make_async
|
||||
from vllm.utils.network_utils import (
|
||||
get_distributed_init_method,
|
||||
get_ip,
|
||||
|
||||
@@ -5,7 +5,7 @@ from typing import TYPE_CHECKING, Literal, NamedTuple, TypeAlias, TypedDict, cas
|
||||
|
||||
from typing_extensions import TypeIs
|
||||
|
||||
from vllm.utils.collections import is_list_of
|
||||
from vllm.utils.collection_utils import is_list_of
|
||||
|
||||
from .data import (
|
||||
EmbedsPrompt,
|
||||
|
||||
@@ -17,7 +17,7 @@ from vllm.logger import init_logger
|
||||
from vllm.model_executor.custom_op import CustomOp
|
||||
from vllm.model_executor.utils import set_weight_attrs
|
||||
from vllm.platforms import current_platform
|
||||
from vllm.utils.collections import LazyDict
|
||||
from vllm.utils.collection_utils import LazyDict
|
||||
|
||||
logger = init_logger(__name__)
|
||||
|
||||
|
||||
@@ -31,7 +31,7 @@ from vllm.utils.deep_gemm import (
|
||||
get_mk_alignment_for_contiguous_layout,
|
||||
m_grouped_fp8_gemm_nt_contiguous,
|
||||
)
|
||||
from vllm.utils.functools import run_once
|
||||
from vllm.utils.func_utils import run_once
|
||||
|
||||
logger = init_logger(__name__)
|
||||
|
||||
|
||||
@@ -28,7 +28,7 @@ from vllm.model_executor.parameter import (
|
||||
RowvLLMParameter,
|
||||
)
|
||||
from vllm.transformers_utils.config import get_safetensors_params_metadata
|
||||
from vllm.utils.collections import is_list_of
|
||||
from vllm.utils.collection_utils import is_list_of
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from vllm.model_executor.layers.quantization import QuantizationMethods
|
||||
|
||||
@@ -57,7 +57,7 @@ from vllm.model_executor.parameter import (
|
||||
from vllm.platforms import current_platform
|
||||
from vllm.scalar_type import scalar_types
|
||||
from vllm.transformers_utils.config import get_safetensors_params_metadata
|
||||
from vllm.utils.collections import is_list_of
|
||||
from vllm.utils.collection_utils import is_list_of
|
||||
|
||||
logger = init_logger(__name__)
|
||||
|
||||
|
||||
@@ -48,7 +48,7 @@ from vllm.transformers_utils.configs.deepseek_vl2 import (
|
||||
)
|
||||
from vllm.transformers_utils.processors.deepseek_vl2 import DeepseekVLV2Processor
|
||||
from vllm.transformers_utils.tokenizer import cached_tokenizer_from_config
|
||||
from vllm.utils.collections import is_list_of
|
||||
from vllm.utils.collection_utils import is_list_of
|
||||
from vllm.utils.tensor_schema import TensorSchema, TensorShape
|
||||
from vllm.utils.torch_utils import set_default_torch_dtype
|
||||
|
||||
|
||||
@@ -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.functools import supports_kw
|
||||
from vllm.utils.func_utils import supports_kw
|
||||
|
||||
from .interfaces_base import VllmModel, is_pooling_model
|
||||
|
||||
|
||||
@@ -15,7 +15,7 @@ import torch.nn as nn
|
||||
from typing_extensions import TypeIs, TypeVar
|
||||
|
||||
from vllm.logger import init_logger
|
||||
from vllm.utils.functools import supports_kw
|
||||
from vllm.utils.func_utils import supports_kw
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from vllm.config import VllmConfig
|
||||
|
||||
@@ -33,7 +33,7 @@ from vllm.multimodal.processing import (
|
||||
)
|
||||
from vllm.multimodal.profiling import BaseDummyInputsBuilder
|
||||
from vllm.sequence import IntermediateTensors
|
||||
from vllm.utils.collections import is_list_of
|
||||
from vllm.utils.collection_utils import is_list_of
|
||||
from vllm.utils.tensor_schema import TensorSchema, TensorShape
|
||||
|
||||
from .interfaces import MultiModalEmbeddings, SupportsMultiModal, SupportsPP
|
||||
|
||||
@@ -85,7 +85,7 @@ from vllm.multimodal.processing import (
|
||||
from vllm.multimodal.profiling import BaseDummyInputsBuilder
|
||||
from vllm.platforms import current_platform
|
||||
from vllm.sequence import IntermediateTensors
|
||||
from vllm.utils.collections import flatten_2d_lists
|
||||
from vllm.utils.collection_utils import flatten_2d_lists
|
||||
from vllm.utils.tensor_schema import TensorSchema, TensorShape
|
||||
from vllm.utils.torch_utils import set_default_torch_dtype
|
||||
|
||||
|
||||
@@ -79,7 +79,7 @@ from vllm.multimodal.processing import (
|
||||
)
|
||||
from vllm.multimodal.profiling import BaseDummyInputsBuilder
|
||||
from vllm.sequence import IntermediateTensors
|
||||
from vllm.utils.collections import is_list_of
|
||||
from vllm.utils.collection_utils import is_list_of
|
||||
|
||||
from .interfaces import (
|
||||
MultiModalEmbeddings,
|
||||
|
||||
@@ -22,7 +22,7 @@ from typing import (
|
||||
import numpy as np
|
||||
from typing_extensions import NotRequired, TypeVar, deprecated
|
||||
|
||||
from vllm.utils.collections import full_groupby, is_list_of
|
||||
from vllm.utils.collection_utils import full_groupby, is_list_of
|
||||
from vllm.utils.import_utils import LazyLoader
|
||||
from vllm.utils.jsontree import json_map_leaves
|
||||
|
||||
|
||||
@@ -19,7 +19,7 @@ import numpy as np
|
||||
import torch
|
||||
from typing_extensions import assert_never
|
||||
|
||||
from vllm.utils.collections import is_list_of
|
||||
from vllm.utils.collection_utils import is_list_of
|
||||
from vllm.utils.import_utils import LazyLoader
|
||||
|
||||
from .audio import AudioResampler
|
||||
|
||||
@@ -25,8 +25,8 @@ from typing_extensions import TypeVar, assert_never
|
||||
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.collections import flatten_2d_lists, full_groupby
|
||||
from vllm.utils.functools import get_allowed_kwarg_only_overrides
|
||||
from vllm.utils.collection_utils import flatten_2d_lists, full_groupby
|
||||
from vllm.utils.func_utils import get_allowed_kwarg_only_overrides
|
||||
from vllm.utils.jsontree import JSONTree, json_map_leaves
|
||||
|
||||
from .hasher import MultiModalHasher
|
||||
@@ -486,7 +486,7 @@ _M = TypeVar("_M", bound=_HasModalityAttr | _HasModalityProp)
|
||||
def full_groupby_modality(values: Iterable[_M]) -> ItemsView[str, list[_M]]:
|
||||
"""
|
||||
Convenience function to apply
|
||||
[`full_groupby`][vllm.utils.collections.full_groupby]
|
||||
[`full_groupby`][vllm.utils.collection_utils.full_groupby]
|
||||
based on modality.
|
||||
"""
|
||||
return full_groupby(values, key=lambda x: x.modality)
|
||||
|
||||
@@ -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 (
|
||||
|
||||
@@ -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:
|
||||
|
||||
+1
-1
@@ -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"]
|
||||
|
||||
|
||||
@@ -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
|
||||
|
||||
@@ -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.
|
||||
|
||||
@@ -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
|
||||
|
||||
@@ -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,
|
||||
|
||||
@@ -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 (
|
||||
|
||||
@@ -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
|
||||
|
||||
Reference in New Issue
Block a user