[Misc] mv chat_utils.py to renderers. (#60522)
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
This commit is contained in:
@@ -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
|
||||
|
||||
Reference in New Issue
Block a user