[Misc] mv chat_utils.py to renderers. (#60522)
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
This commit is contained in:
@@ -35,7 +35,6 @@ from vllm.entrypoints.anthropic.protocol import (
|
||||
AnthropicToolChangeDefinition,
|
||||
AnthropicUsage,
|
||||
)
|
||||
from vllm.entrypoints.chat_utils import ChatTemplateContentFormatOption
|
||||
from vllm.entrypoints.generate.base.protocol import (
|
||||
JsonSchemaResponseFormat,
|
||||
ResponseFormat,
|
||||
@@ -54,6 +53,7 @@ from vllm.entrypoints.serve.engine.protocol import ErrorResponse, UsageInfo
|
||||
from vllm.entrypoints.serve.exception_handling.utils import sanitize_message
|
||||
from vllm.entrypoints.serve.utils.request_logger import RequestLogger
|
||||
from vllm.logger import init_logger
|
||||
from vllm.renderers.chat_utils import ChatTemplateContentFormatOption
|
||||
from vllm.renderers.hf import HfRenderer, resolve_chat_template
|
||||
from vllm.renderers.online_renderer import OnlineRenderer
|
||||
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -45,7 +45,6 @@ from fastapi import Request
|
||||
from pydantic import BaseModel
|
||||
|
||||
from vllm.engine.protocol import EngineClient
|
||||
from vllm.entrypoints.chat_utils import ChatTemplateContentFormatOption
|
||||
from vllm.entrypoints.cohere.cohere_chat_message import (
|
||||
CitationSource as InternalCitationSource,
|
||||
)
|
||||
@@ -91,6 +90,7 @@ from vllm.entrypoints.serve.engine.protocol import ErrorInfo, ErrorResponse
|
||||
from vllm.entrypoints.serve.exception_handling.utils import sanitize_message
|
||||
from vllm.entrypoints.serve.utils.request_logger import RequestLogger
|
||||
from vllm.parser.abstract_parser import Parser
|
||||
from vllm.renderers.chat_utils import ChatTemplateContentFormatOption
|
||||
from vllm.renderers.cohere import (
|
||||
MESSAGES_CITATIONS_KEY,
|
||||
POSITION_TO_SOURCE_KEY,
|
||||
@@ -509,7 +509,7 @@ class CohereServingChatV2(OpenAIServingChat):
|
||||
# ``TextToolContent`` and ``DocumentToolContent``. The latter
|
||||
# produces ``{"type": "document", "document": {...}}`` blocks,
|
||||
# which vLLM's shared ``_parse_chat_message_content_parts`` in
|
||||
# ``vllm/entrypoints/chat_utils.py`` rejects because the OpenAI
|
||||
# ``vllm/renderers/chat_utils.py`` rejects because the OpenAI
|
||||
# ``ChatCompletionContentPartParam`` union only knows text /
|
||||
# image / audio / etc. Emitting them anyway triggers a Pydantic
|
||||
# ``ValidatorIterator`` failure at chat-parsing time, so we
|
||||
|
||||
@@ -15,15 +15,15 @@ from vllm import (
|
||||
SamplingParams,
|
||||
)
|
||||
from vllm.config import ModelConfig
|
||||
from vllm.entrypoints.chat_utils import (
|
||||
ChatCompletionMessageParam,
|
||||
ChatTemplateContentFormatOption,
|
||||
)
|
||||
from vllm.exceptions import VLLMValidationError
|
||||
from vllm.inputs import EngineInput
|
||||
from vllm.logger import init_logger
|
||||
from vllm.lora.request import LoRARequest
|
||||
from vllm.renderers import BaseRenderer, ChatParams, merge_kwargs
|
||||
from vllm.renderers.chat_utils import (
|
||||
ChatCompletionMessageParam,
|
||||
ChatTemplateContentFormatOption,
|
||||
)
|
||||
from vllm.renderers.inputs.preprocess import (
|
||||
conversation_to_seq,
|
||||
parse_model_prompt,
|
||||
|
||||
@@ -72,7 +72,7 @@ async def init_generate_state(
|
||||
default_chat_template_kwargs: dict[str, Any],
|
||||
):
|
||||
from vllm.entrypoints.anthropic.serving import AnthropicServingMessages
|
||||
from vllm.entrypoints.chat_utils import load_chat_template
|
||||
from vllm.renderers.chat_utils import load_chat_template
|
||||
|
||||
# The Cohere serving handler depends on the optional `cohere` SDK for
|
||||
# its wire-format protocol models, and is additionally gated on the
|
||||
|
||||
@@ -15,10 +15,10 @@ from pydantic import (
|
||||
|
||||
import vllm.envs as envs
|
||||
from vllm.config.utils import replace
|
||||
from vllm.entrypoints.chat_utils import make_tool_call_id
|
||||
from vllm.entrypoints.serve.engine.protocol import OpenAIBaseModel, UsageInfo
|
||||
from vllm.exceptions import VLLMValidationError
|
||||
from vllm.logger import init_logger
|
||||
from vllm.renderers.chat_utils import make_tool_call_id
|
||||
from vllm.sampling_params import StructuredOutputsParams
|
||||
|
||||
logger = init_logger(__name__)
|
||||
|
||||
@@ -8,10 +8,10 @@ from typing import Any, Literal
|
||||
from pydantic import Field, model_validator
|
||||
|
||||
from vllm.config import ModelConfig
|
||||
from vllm.entrypoints.chat_utils import ChatTemplateContentFormatOption
|
||||
from vllm.entrypoints.generate.base.protocol import validate_cache_salt
|
||||
from vllm.entrypoints.serve.engine.protocol import OpenAIBaseModel
|
||||
from vllm.renderers import ChatParams, TokenizeParams, merge_kwargs
|
||||
from vllm.renderers.chat_utils import ChatTemplateContentFormatOption
|
||||
from vllm.utils import random_uuid
|
||||
|
||||
|
||||
|
||||
@@ -16,10 +16,10 @@ from typing import Any
|
||||
|
||||
from vllm.config import ModelConfig
|
||||
from vllm.engine.protocol import EngineClient
|
||||
from vllm.entrypoints.chat_utils import ChatTemplateContentFormatOption
|
||||
from vllm.entrypoints.generate.label_reads import next_token_label_reads
|
||||
from vllm.inputs import EngineInput, tokens_input
|
||||
from vllm.lora.request import LoRARequest
|
||||
from vllm.renderers.chat_utils import ChatTemplateContentFormatOption
|
||||
from vllm.renderers.inputs.preprocess import extract_prompt_components
|
||||
from vllm.renderers.online_renderer import OnlineRenderer
|
||||
from vllm.sampling_params import SamplingParams
|
||||
|
||||
@@ -7,7 +7,6 @@ from typing import cast
|
||||
from starlette.datastructures import State
|
||||
|
||||
from vllm.engine.protocol import EngineClient
|
||||
from vllm.entrypoints.chat_utils import load_chat_template
|
||||
from vllm.entrypoints.launchers.cli_args import resolve_default_chat_template_kwargs
|
||||
from vllm.entrypoints.mcp.tool_server import init_tool_server
|
||||
from vllm.entrypoints.openai.models.protocol import BaseModelPath
|
||||
@@ -16,6 +15,7 @@ from vllm.entrypoints.serve.tokenize.serving import ServingTokenization
|
||||
from vllm.entrypoints.serve.utils.api_utils import process_lora_modules
|
||||
from vllm.entrypoints.serve.utils.request_logger import RequestLogger
|
||||
from vllm.plugins.endpoint_plugins.interface import init_endpoint_plugins_state
|
||||
from vllm.renderers.chat_utils import load_chat_template
|
||||
from vllm.renderers.online_derenderer import OnlineDerenderer
|
||||
from vllm.renderers.online_renderer import OnlineRenderer
|
||||
from vllm.tasks import FALLBACK_SUPPORTED_TASKS, POOLING_TASKS, SupportedTask
|
||||
|
||||
@@ -17,12 +17,12 @@ from vllm.engine.arg_utils import AsyncEngineArgs, optional_type
|
||||
from vllm.entrypoints.anthropic.protocol import (
|
||||
AnthropicDisabledThinkingEffortOption,
|
||||
)
|
||||
from vllm.entrypoints.chat_utils import (
|
||||
from vllm.entrypoints.openai.models.protocol import LoRAModulePath
|
||||
from vllm.logger import init_logger
|
||||
from vllm.renderers.chat_utils import (
|
||||
ChatTemplateContentFormatOption,
|
||||
validate_chat_template,
|
||||
)
|
||||
from vllm.entrypoints.openai.models.protocol import LoRAModulePath
|
||||
from vllm.logger import init_logger
|
||||
from vllm.tool_parsers import ToolParserManager
|
||||
from vllm.tool_parsers.tool_strict_level import ToolStrictLevelName
|
||||
from vllm.utils.argparse_utils import FlexibleArgumentParser
|
||||
|
||||
@@ -5,7 +5,6 @@ from argparse import Namespace
|
||||
from starlette.datastructures import State
|
||||
|
||||
from vllm.config import VllmConfig
|
||||
from vllm.entrypoints.chat_utils import load_chat_template
|
||||
from vllm.entrypoints.launchers.cli_args import resolve_default_chat_template_kwargs
|
||||
from vllm.entrypoints.mcp.tool_server import init_tool_server
|
||||
from vllm.entrypoints.openai.models.protocol import BaseModelPath
|
||||
@@ -15,6 +14,7 @@ from vllm.entrypoints.serve.tokenize.serving import ServingTokenization
|
||||
from vllm.entrypoints.serve.utils.request_logger import RequestLogger
|
||||
from vllm.plugins.endpoint_plugins.interface import init_endpoint_plugins_state
|
||||
from vllm.renderers import renderer_from_config
|
||||
from vllm.renderers.chat_utils import load_chat_template
|
||||
from vllm.renderers.online_derenderer import OnlineDerenderer
|
||||
from vllm.renderers.online_renderer import OnlineRenderer
|
||||
|
||||
|
||||
@@ -28,11 +28,6 @@ from vllm.config.model import (
|
||||
)
|
||||
from vllm.config.quantization import QuantizationConfigArgs
|
||||
from vllm.engine.arg_utils import EngineArgs
|
||||
from vllm.entrypoints.chat_utils import (
|
||||
ChatCompletionMessageParam,
|
||||
ChatTemplateContentFormatOption,
|
||||
load_chat_template,
|
||||
)
|
||||
from vllm.entrypoints.common.offline import _O, _R, OfflineInferenceMixin
|
||||
from vllm.entrypoints.generate.beam_search.offline import BeamSearchOfflineMixin
|
||||
from vllm.entrypoints.pooling.offline import PoolingOfflineMixin
|
||||
@@ -44,6 +39,11 @@ from vllm.lora.request import LoRARequest
|
||||
from vllm.model_executor.layers.quantization import QuantizationMethods
|
||||
from vllm.outputs import PoolingRequestOutput, RequestOutput
|
||||
from vllm.platforms import current_platform
|
||||
from vllm.renderers.chat_utils import (
|
||||
ChatCompletionMessageParam,
|
||||
ChatTemplateContentFormatOption,
|
||||
load_chat_template,
|
||||
)
|
||||
from vllm.sampling_params import SamplingParams
|
||||
from vllm.tokenizers import TokenizerLike
|
||||
from vllm.usage.usage_lib import UsageContext
|
||||
|
||||
@@ -8,7 +8,6 @@ from http import HTTPStatus
|
||||
|
||||
from fastapi import Request
|
||||
|
||||
from vllm.entrypoints.chat_utils import ConversationMessage
|
||||
from vllm.entrypoints.generate.base.protocol import RequestResponseMetadata
|
||||
from vllm.entrypoints.openai.chat_completion.protocol import (
|
||||
BatchChatCompletionRequest,
|
||||
@@ -24,6 +23,7 @@ from vllm.inputs import EngineInput
|
||||
from vllm.logger import init_logger
|
||||
from vllm.outputs import RequestOutput
|
||||
from vllm.parser.abstract_parser import Parser
|
||||
from vllm.renderers.chat_utils import ConversationMessage
|
||||
from vllm.tokenizers import TokenizerLike
|
||||
from vllm.utils.async_utils import merge_async_iterators
|
||||
from vllm.utils.collection_utils import as_list
|
||||
|
||||
@@ -19,11 +19,6 @@ from pydantic import (
|
||||
)
|
||||
|
||||
from vllm.config import ModelConfig
|
||||
from vllm.entrypoints.chat_utils import (
|
||||
ChatCompletionMessageParam,
|
||||
ChatTemplateContentFormatOption,
|
||||
has_non_text_content,
|
||||
)
|
||||
from vllm.entrypoints.generate.base.protocol import (
|
||||
AnyResponseFormat,
|
||||
DeltaMessage,
|
||||
@@ -44,6 +39,11 @@ from vllm.exceptions import VLLMValidationError
|
||||
from vllm.logger import init_logger
|
||||
from vllm.logprobs import Logprob
|
||||
from vllm.renderers import ChatParams, TokenizeParams, merge_kwargs
|
||||
from vllm.renderers.chat_utils import (
|
||||
ChatCompletionMessageParam,
|
||||
ChatTemplateContentFormatOption,
|
||||
has_non_text_content,
|
||||
)
|
||||
from vllm.sampling_params import (
|
||||
BeamSearchParams,
|
||||
RepetitionDetectionParams,
|
||||
|
||||
@@ -11,11 +11,6 @@ from typing import Any, Final, cast
|
||||
from fastapi import Request
|
||||
|
||||
from vllm.engine.protocol import EngineClient
|
||||
from vllm.entrypoints.chat_utils import (
|
||||
ChatTemplateContentFormatOption,
|
||||
ConversationMessage,
|
||||
make_tool_call_id,
|
||||
)
|
||||
from vllm.entrypoints.generate.base.protocol import (
|
||||
DeltaMessage,
|
||||
FunctionCall,
|
||||
@@ -61,6 +56,11 @@ from vllm.logprobs import Logprob
|
||||
from vllm.outputs import RequestOutput
|
||||
from vllm.parser import ParserManager
|
||||
from vllm.parser.abstract_parser import Parser
|
||||
from vllm.renderers.chat_utils import (
|
||||
ChatTemplateContentFormatOption,
|
||||
ConversationMessage,
|
||||
make_tool_call_id,
|
||||
)
|
||||
from vllm.renderers.online_renderer import OnlineRenderer
|
||||
from vllm.sampling_params import BeamSearchParams, SamplingParams
|
||||
from vllm.tokenizers import TokenizerLike
|
||||
|
||||
@@ -21,9 +21,6 @@ from openai.types.responses.tool import Mcp
|
||||
from openai_harmony import Author, Message, Role, TextContent
|
||||
|
||||
from vllm import envs
|
||||
from vllm.entrypoints.chat_utils import (
|
||||
ChatTemplateContentFormatOption,
|
||||
)
|
||||
from vllm.entrypoints.mcp.tool import Tool
|
||||
from vllm.entrypoints.mcp.tool_server import ToolServer
|
||||
from vllm.entrypoints.openai.parser.harmony_utils import render_for_completion
|
||||
@@ -41,6 +38,9 @@ from vllm.entrypoints.serve.utils.tool_calls_utils import (
|
||||
)
|
||||
from vllm.outputs import RequestOutput
|
||||
from vllm.parser.abstract_parser import Parser
|
||||
from vllm.renderers.chat_utils import (
|
||||
ChatTemplateContentFormatOption,
|
||||
)
|
||||
from vllm.tokenizers import TokenizerLike
|
||||
from vllm.utils import random_uuid
|
||||
|
||||
|
||||
@@ -54,10 +54,6 @@ from pydantic import (
|
||||
)
|
||||
|
||||
from vllm.config import ModelConfig
|
||||
from vllm.entrypoints.chat_utils import (
|
||||
ChatCompletionMessageParam,
|
||||
ChatTemplateContentFormatOption,
|
||||
)
|
||||
from vllm.entrypoints.generate.base.protocol import (
|
||||
PerRequestMetrics,
|
||||
StopParam,
|
||||
@@ -68,6 +64,10 @@ from vllm.entrypoints.serve.engine.protocol import OpenAIBaseModel
|
||||
from vllm.exceptions import VLLMValidationError
|
||||
from vllm.logger import init_logger
|
||||
from vllm.renderers import ChatParams, TokenizeParams, merge_kwargs
|
||||
from vllm.renderers.chat_utils import (
|
||||
ChatCompletionMessageParam,
|
||||
ChatTemplateContentFormatOption,
|
||||
)
|
||||
from vllm.sampling_params import (
|
||||
RequestOutputKind,
|
||||
SamplingParams,
|
||||
|
||||
@@ -23,9 +23,6 @@ from pydantic import TypeAdapter
|
||||
from vllm import envs
|
||||
from vllm.config.utils import replace
|
||||
from vllm.engine.protocol import EngineClient
|
||||
from vllm.entrypoints.chat_utils import (
|
||||
ChatTemplateContentFormatOption,
|
||||
)
|
||||
from vllm.entrypoints.generate.base.protocol import (
|
||||
DeltaMessage,
|
||||
RequestResponseMetadata,
|
||||
@@ -86,6 +83,9 @@ from vllm.lora.request import LoRARequest
|
||||
from vllm.outputs import CompletionOutput
|
||||
from vllm.parser import Parser, ParserManager
|
||||
from vllm.renderers import TokenizeParams
|
||||
from vllm.renderers.chat_utils import (
|
||||
ChatTemplateContentFormatOption,
|
||||
)
|
||||
from vllm.renderers.online_renderer import (
|
||||
OnlineRenderer,
|
||||
ResponsesPreviousMessages,
|
||||
|
||||
@@ -62,7 +62,6 @@ from openai.types.responses.response_reasoning_item import (
|
||||
from openai.types.responses.tool import Tool
|
||||
from openai_harmony import Message as HarmonyMessage
|
||||
|
||||
from vllm.entrypoints.chat_utils import make_tool_call_id
|
||||
from vllm.entrypoints.generate.base.protocol import DeltaMessage, DeltaToolCall
|
||||
from vllm.entrypoints.mcp.tool_server import ToolServer
|
||||
from vllm.entrypoints.openai.parser.harmony_utils import (
|
||||
@@ -78,6 +77,7 @@ from vllm.entrypoints.openai.responses.utils import (
|
||||
)
|
||||
from vllm.outputs import CompletionOutput
|
||||
from vllm.parser.harmony import Segment
|
||||
from vllm.renderers.chat_utils import make_tool_call_id
|
||||
from vllm.utils import random_uuid
|
||||
|
||||
TOOL_NAME_TO_MCP_SERVER_LABEL: Final[dict[str, str]] = {
|
||||
|
||||
@@ -30,7 +30,6 @@ from openai.types.responses.response_reasoning_item import (
|
||||
from openai.types.responses.tool import Tool
|
||||
|
||||
from vllm import envs
|
||||
from vllm.entrypoints.chat_utils import make_tool_call_id
|
||||
from vllm.entrypoints.generate.base.protocol import FunctionCall, FunctionDefinition
|
||||
from vllm.entrypoints.openai.chat_completion.protocol import (
|
||||
ChatCompletionMessageParam,
|
||||
@@ -39,6 +38,7 @@ from vllm.entrypoints.openai.chat_completion.protocol import (
|
||||
from vllm.entrypoints.openai.responses.protocol import ResponseInputOutputItem
|
||||
from vllm.exceptions import VLLMValidationError
|
||||
from vllm.logger import init_logger
|
||||
from vllm.renderers.chat_utils import make_tool_call_id
|
||||
from vllm.tool_parsers.utils import (
|
||||
build_responses_tool_call_name_map,
|
||||
flat_namespace_tool_name,
|
||||
|
||||
@@ -10,12 +10,12 @@ from vllm import (
|
||||
PoolingRequestOutput,
|
||||
)
|
||||
from vllm.config import VllmConfig
|
||||
from vllm.entrypoints.chat_utils import (
|
||||
ChatTemplateConfig,
|
||||
)
|
||||
from vllm.exceptions import VLLMValidationError
|
||||
from vllm.lora.request import LoRARequest
|
||||
from vllm.renderers import BaseRenderer, merge_kwargs
|
||||
from vllm.renderers.chat_utils import (
|
||||
ChatTemplateConfig,
|
||||
)
|
||||
from vllm.renderers.inputs.preprocess import parse_model_prompt, prompt_to_seq
|
||||
from vllm.utils.async_utils import make_async
|
||||
from vllm.utils.mistral import is_mistral_tokenizer
|
||||
|
||||
@@ -7,14 +7,14 @@ from typing import Annotated, Any, Literal
|
||||
from pydantic import Field, model_validator
|
||||
|
||||
from vllm.config import ModelConfig
|
||||
from vllm.entrypoints.chat_utils import (
|
||||
ChatCompletionMessageParam,
|
||||
ChatTemplateContentFormatOption,
|
||||
)
|
||||
from vllm.entrypoints.generate.base.protocol import validate_cache_salt
|
||||
from vllm.entrypoints.serve.engine.protocol import OpenAIBaseModel
|
||||
from vllm.exceptions import VLLMValidationError
|
||||
from vllm.renderers import ChatParams, TokenizeParams, merge_kwargs
|
||||
from vllm.renderers.chat_utils import (
|
||||
ChatCompletionMessageParam,
|
||||
ChatTemplateContentFormatOption,
|
||||
)
|
||||
from vllm.tasks import check_removed_pooling_task
|
||||
from vllm.utils import random_uuid
|
||||
from vllm.utils.serial_utils import EmbedDType, EncodingFormat, Endianness
|
||||
|
||||
@@ -14,7 +14,6 @@ from fastapi.responses import Response
|
||||
from vllm import PoolingRequestOutput, envs
|
||||
from vllm.config import VllmConfig
|
||||
from vllm.engine.protocol import EngineClient
|
||||
from vllm.entrypoints.chat_utils import ChatTemplateConfig
|
||||
from vllm.entrypoints.generate.base.protocol import validate_request_mm_kwargs
|
||||
from vllm.entrypoints.openai.models.serving import OpenAIServingModels
|
||||
from vllm.entrypoints.serve.engine.serving import BaseServing
|
||||
@@ -23,6 +22,7 @@ from vllm.entrypoints.serve.utils.request_logger import RequestLogger
|
||||
from vllm.exceptions import GenerationError, RetryableRequestError
|
||||
from vllm.lora.request import LoRARequest
|
||||
from vllm.renderers.base import BaseRenderer
|
||||
from vllm.renderers.chat_utils import ChatTemplateConfig
|
||||
from vllm.utils.async_utils import make_async, merge_async_iterators
|
||||
|
||||
from ...serve.engine.protocol import ErrorResponse
|
||||
|
||||
@@ -12,15 +12,15 @@ from openai.types.chat import (
|
||||
from openai.types.chat.chat_completion_content_part_image_param import ImageURL
|
||||
|
||||
from vllm import PoolingParams
|
||||
from vllm.entrypoints.chat_utils import (
|
||||
ChatCompletionContentPartParam,
|
||||
ChatCompletionMessageParam,
|
||||
CustomChatCompletionMessageParam,
|
||||
)
|
||||
from vllm.inputs import tokens_input
|
||||
from vllm.logger import init_logger
|
||||
from vllm.outputs import PoolingOutput, PoolingRequestOutput
|
||||
from vllm.renderers import merge_kwargs
|
||||
from vllm.renderers.chat_utils import (
|
||||
ChatCompletionContentPartParam,
|
||||
ChatCompletionMessageParam,
|
||||
CustomChatCompletionMessageParam,
|
||||
)
|
||||
from vllm.renderers.hf import resolve_chat_template
|
||||
from vllm.utils.collection_utils import chunk_list
|
||||
from vllm.utils.mistral import is_mistral_tokenizer
|
||||
|
||||
@@ -17,8 +17,8 @@ import pybase64 as base64
|
||||
from pydantic import BaseModel, BeforeValidator, Field, model_validator
|
||||
|
||||
from vllm import PoolingParams
|
||||
from vllm.entrypoints.chat_utils import ChatCompletionMessageParam
|
||||
from vllm.entrypoints.serve.engine.protocol import OpenAIBaseModel, UsageInfo
|
||||
from vllm.renderers.chat_utils import ChatCompletionMessageParam
|
||||
from vllm.utils import random_uuid
|
||||
|
||||
from ..base.protocol import (
|
||||
|
||||
@@ -6,10 +6,10 @@ from typing import TYPE_CHECKING
|
||||
from fastapi import FastAPI
|
||||
|
||||
from vllm.config import ModelConfig, VllmConfig
|
||||
from vllm.entrypoints.chat_utils import ChatTemplateConfig
|
||||
from vllm.logger import init_logger
|
||||
from vllm.plugins.io_processors import has_io_processor
|
||||
from vllm.renderers import BaseRenderer
|
||||
from vllm.renderers.chat_utils import ChatTemplateConfig
|
||||
from vllm.tasks import POOLING_TASKS, SCORE_TYPE_MAP, SupportedTask
|
||||
|
||||
from .base.io_processor import PoolingIOProcessor
|
||||
@@ -151,7 +151,7 @@ def init_pooling_state(
|
||||
if model_config is None:
|
||||
return
|
||||
|
||||
from vllm.entrypoints.chat_utils import load_chat_template
|
||||
from vllm.renderers.chat_utils import load_chat_template
|
||||
from vllm.tasks import POOLING_TASKS
|
||||
|
||||
from .classify.serving import ServingClassification
|
||||
|
||||
@@ -6,7 +6,6 @@ from typing import Any
|
||||
|
||||
from tqdm.auto import tqdm
|
||||
|
||||
from vllm.entrypoints.chat_utils import ChatTemplateConfig
|
||||
from vllm.entrypoints.common.offline import OfflineInferenceMixin
|
||||
from vllm.inputs import DataPrompt, PromptType
|
||||
from vllm.logger import init_logger
|
||||
@@ -18,6 +17,7 @@ from vllm.outputs import (
|
||||
ScoringRequestOutput,
|
||||
)
|
||||
from vllm.pooling_params import PoolingParams
|
||||
from vllm.renderers.chat_utils import ChatTemplateConfig
|
||||
from vllm.tasks import SCORE_TYPE_MAP, PoolingTask, SupportedTask
|
||||
|
||||
from .base.io_processor import PoolingIOProcessor
|
||||
|
||||
@@ -9,6 +9,7 @@ import torch.nn.functional as F
|
||||
from vllm import PoolingParams, PoolingRequestOutput, TokensPrompt
|
||||
from vllm.logger import init_logger
|
||||
from vllm.renderers import TokenizeParams
|
||||
from vllm.renderers.chat_utils import ChatTemplateResolutionError
|
||||
from vllm.renderers.hf import safe_apply_chat_template
|
||||
from vllm.renderers.inputs.preprocess import (
|
||||
extract_target_prompt,
|
||||
@@ -18,7 +19,6 @@ from vllm.renderers.inputs.preprocess import (
|
||||
from vllm.tasks import PoolingTask
|
||||
from vllm.utils.mistral import is_mistral_tokenizer
|
||||
|
||||
from ...chat_utils import ChatTemplateResolutionError
|
||||
from ..base.io_processor import PoolingIOProcessor
|
||||
from ..pooling.protocol import PoolingCompletionRequest
|
||||
from ..typing import (
|
||||
|
||||
@@ -5,7 +5,7 @@ from typing import Required, TypeAlias
|
||||
|
||||
from typing_extensions import TypedDict
|
||||
|
||||
from vllm.entrypoints.chat_utils import (
|
||||
from vllm.renderers.chat_utils import (
|
||||
ChatCompletionContentPartImageEmbedsParam,
|
||||
ChatCompletionContentPartImageParam,
|
||||
ChatCompletionContentPartTextParam,
|
||||
|
||||
@@ -7,7 +7,9 @@ import torch
|
||||
|
||||
from vllm import PromptType, TextPrompt
|
||||
from vllm.config import ModelConfig
|
||||
from vllm.entrypoints.chat_utils import (
|
||||
from vllm.exceptions import VLLMValidationError
|
||||
from vllm.inputs import MultiModalDataDict, MultiModalUUIDDict
|
||||
from vllm.renderers.chat_utils import (
|
||||
BaseMultiModalItemTracker,
|
||||
ChatCompletionContentPartParam,
|
||||
ChatCompletionContentPartTextParam,
|
||||
@@ -15,8 +17,6 @@ from vllm.entrypoints.chat_utils import (
|
||||
MultiModalItemTracker,
|
||||
_parse_chat_message_content_parts,
|
||||
)
|
||||
from vllm.exceptions import VLLMValidationError
|
||||
from vllm.inputs import MultiModalDataDict, MultiModalUUIDDict
|
||||
|
||||
from .typing import (
|
||||
ScoreContentPartParam,
|
||||
|
||||
@@ -9,10 +9,10 @@ from fastapi import Request
|
||||
from pydantic import ConfigDict
|
||||
|
||||
from vllm import PoolingParams, PoolingRequestOutput, PromptType
|
||||
from vllm.entrypoints.chat_utils import ChatCompletionMessageParam
|
||||
from vllm.inputs import DataPrompt, EngineInput
|
||||
from vllm.lora.request import LoRARequest
|
||||
from vllm.renderers import ChatParams, TokenizeParams
|
||||
from vllm.renderers.chat_utils import ChatCompletionMessageParam
|
||||
from vllm.renderers.inputs import DictPrompt
|
||||
|
||||
from ...tasks import PoolingTask
|
||||
|
||||
@@ -13,7 +13,6 @@ import msgspec
|
||||
from fastapi import Request
|
||||
|
||||
from vllm.engine.protocol import EngineClient
|
||||
from vllm.entrypoints.chat_utils import AsyncMultiModalItemTracker
|
||||
from vllm.entrypoints.generate.base.protocol import (
|
||||
PerRequestMetrics,
|
||||
RequestResponseMetadata,
|
||||
@@ -47,6 +46,7 @@ from vllm.multimodal.inputs import (
|
||||
PlaceholderRange,
|
||||
)
|
||||
from vllm.outputs import RequestOutput
|
||||
from vllm.renderers.chat_utils import AsyncMultiModalItemTracker
|
||||
from vllm.renderers.online_renderer import OnlineRenderer
|
||||
from vllm.sampling_params import RequestOutputKind, SamplingParams
|
||||
from vllm.tokenizers import TokenizerLike
|
||||
|
||||
@@ -4,7 +4,6 @@
|
||||
from typing import Protocol, TypeAlias
|
||||
|
||||
from vllm.config import ModelConfig
|
||||
from vllm.entrypoints.chat_utils import ChatTemplateContentFormatOption
|
||||
from vllm.entrypoints.openai.chat_completion.protocol import (
|
||||
BatchChatCompletionRequest,
|
||||
ChatCompletionRequest,
|
||||
@@ -35,6 +34,7 @@ from vllm.entrypoints.speech_to_text.transcription.protocol import (
|
||||
)
|
||||
from vllm.entrypoints.speech_to_text.translation.protocol import TranslationRequest
|
||||
from vllm.renderers import ChatParams, TokenizeParams
|
||||
from vllm.renderers.chat_utils import ChatTemplateContentFormatOption
|
||||
|
||||
|
||||
class RendererRequest(Protocol):
|
||||
|
||||
@@ -7,14 +7,14 @@ from typing import Annotated, Any, TypeAlias
|
||||
from pydantic import ConfigDict, Field, model_validator
|
||||
|
||||
from vllm.config import ModelConfig
|
||||
from vllm.entrypoints.chat_utils import (
|
||||
ChatCompletionMessageParam,
|
||||
ChatTemplateContentFormatOption,
|
||||
)
|
||||
from vllm.entrypoints.openai.chat_completion.protocol import ChatCompletionToolsParam
|
||||
from vllm.entrypoints.serve.engine.protocol import OpenAIBaseModel
|
||||
from vllm.exceptions import VLLMValidationError
|
||||
from vllm.renderers import ChatParams, TokenizeParams, merge_kwargs
|
||||
from vllm.renderers.chat_utils import (
|
||||
ChatCompletionMessageParam,
|
||||
ChatTemplateContentFormatOption,
|
||||
)
|
||||
|
||||
|
||||
class TokenizeCompletionRequest(OpenAIBaseModel):
|
||||
|
||||
@@ -5,7 +5,6 @@ from typing import Any, Final
|
||||
|
||||
from fastapi import Request
|
||||
|
||||
from vllm.entrypoints.chat_utils import ChatTemplateContentFormatOption
|
||||
from vllm.entrypoints.openai.models.serving import (
|
||||
OpenAIModelRegistry,
|
||||
OpenAIServingModels,
|
||||
@@ -23,6 +22,7 @@ from vllm.entrypoints.serve.tokenize.protocol import (
|
||||
from vllm.entrypoints.serve.utils.request_logger import RequestLogger
|
||||
from vllm.inputs import TokensPrompt, tokens_input
|
||||
from vllm.logger import init_logger
|
||||
from vllm.renderers.chat_utils import ChatTemplateContentFormatOption
|
||||
from vllm.renderers.online_renderer import OnlineRenderer
|
||||
from vllm.tokenizers import TokenizerLike
|
||||
|
||||
|
||||
Reference in New Issue
Block a user