423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-08-22 22:02:51 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #3655 from Tendo33/main

Browse Source 
1.Change the name of is_fastapi_available function 2. Added the log of printing requests when deploying using vllm

Former-commit-id: f7c8eddbc584ab788579a53823ffe5b5808883b8
This commit is contained in:
hoshi-hiyouga 2024-05-13 18:05:50 +08:00 committed by GitHub
commit ed546236c0
4 changed files with 14 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
src/llmtuner/api/app.py
View File

@ -6,7 +6,7 @@ from typing_extensions import Annotated
from ..chat import ChatModel from ..chat import ChatModel
from ..extras.misc import torch_gc from ..extras.misc import torch_gc
from ..extras.packages import is_fastapi_availble, is_starlette_available, is_uvicorn_available from ..extras.packages import is_fastapi_available, is_starlette_available, is_uvicorn_available
from .chat import ( from .chat import (
create_chat_completion_response, create_chat_completion_response,
create_score_evaluation_response, create_score_evaluation_response,
@ -22,7 +22,7 @@ from .protocol import (
) )
if is_fastapi_availble(): if is_fastapi_available():
from fastapi import Depends, FastAPI, HTTPException, status from fastapi import Depends, FastAPI, HTTPException, status
from fastapi.middleware.cors import CORSMiddleware from fastapi.middleware.cors import CORSMiddleware
from fastapi.security.http import HTTPAuthorizationCredentials, HTTPBearer from fastapi.security.http import HTTPAuthorizationCredentials, HTTPBearer

10
src/llmtuner/api/chat.py
View File

@ -3,7 +3,8 @@ import uuid
from typing import TYPE_CHECKING, AsyncGenerator, Dict, List, Optional, Tuple from typing import TYPE_CHECKING, AsyncGenerator, Dict, List, Optional, Tuple
from ..data import Role as DataRole from ..data import Role as DataRole
from ..extras.packages import is_fastapi_availble from ..extras.logging import get_logger
from ..extras.packages import is_fastapi_available
from .common import dictify, jsonify from .common import dictify, jsonify
from .protocol import ( from .protocol import (
ChatCompletionMessage, ChatCompletionMessage,
@ -20,7 +21,9 @@ from .protocol import (
) )
if is_fastapi_availble(): logger = get_logger(__name__)
if is_fastapi_available():
from fastapi import HTTPException, status from fastapi import HTTPException, status
@ -39,6 +42,9 @@ ROLE_MAPPING = {
def _process_request(request: "ChatCompletionRequest") -> Tuple[List[Dict[str, str]], str, str]: def _process_request(request: "ChatCompletionRequest") -> Tuple[List[Dict[str, str]], str, str]:
params = dictify(request)
logger.info(f"==== request ====\n{params}")
if len(request.messages) == 0: if len(request.messages) == 0:
raise HTTPException(status_code=status.HTTP_400_BAD_REQUEST, detail="Invalid length") raise HTTPException(status_code=status.HTTP_400_BAD_REQUEST, detail="Invalid length")

6
src/llmtuner/api/common.py
View File

@ -6,11 +6,11 @@ if TYPE_CHECKING:
from pydantic import BaseModel from pydantic import BaseModel
def dictify(data: "BaseModel") -> Dict[str, Any]: def dictify(data: "BaseModel", **kwargs) -> Dict[str, Any]:
try: # pydantic v2 try: # pydantic v2
return data.model_dump(exclude_unset=True) return data.model_dump(**kwargs)
except AttributeError: # pydantic v1 except AttributeError: # pydantic v1
return data.dict(exclude_unset=True) return data.dict(**kwargs)
def jsonify(data: "BaseModel") -> str: def jsonify(data: "BaseModel") -> str:

2
src/llmtuner/extras/packages.py
View File

@ -20,7 +20,7 @@ def _get_package_version(name: str) -> "Version":
return version.parse("0.0.0") return version.parse("0.0.0")
def is_fastapi_availble(): def is_fastapi_available():
return _is_package_available("fastapi") return _is_package_available("fastapi")