vrr/kvcache-ai-ktransformers
2
0
Fork 0
mirror of https://github.com/kvcache-ai/ktransformers.git synced 2025-09-11 07:44:35 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

add balance-serve, support concurrence

Browse source
This commit is contained in:
Atream 2025-03-31 22:55:32 +08:00
parent 8d0292aa44
commit 25cee5810e
196 changed files with 22077 additions and 565 deletions
Download patch file Download diff file Expand all files Collapse all files

6
ktransformers/server/schemas/endpoints/chat.py
View file

@ -2,7 +2,7 @@ from typing import List, Optional
from typing_extensions import Literal
from enum import Enum
from pydantic import BaseModel
from pydantic import BaseModel, Field
from ktransformers.server.schemas.base import Object
@ -30,8 +30,8 @@ class ChatCompletionCreate(BaseModel):
messages: List[Message]
model : str
stream : bool = False
temperature: Optional[float] = None
top_p: Optional[float] = None
temperature: Optional[float] = Field(default=1.0)
top_p: Optional[float] = Field(default=1.0)
def get_tokenizer_messages(self):
return [m.to_tokenizer_message() for m in self.messages]