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