[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
|
||||
|
||||
Reference in New Issue
Block a user