vrr/kvcache-ai-ktransformers
2
0
Fork 0
mirror of https://github.com/kvcache-ai/ktransformers.git synced 2025-09-10 23:34:35 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

update speed test

Browse source
This commit is contained in:
qiyuxinlin 2025-04-22 07:38:05 +00:00
parent f5287e908a
commit b17ab8653c
4 changed files with 66 additions and 31 deletions
Download patch file Download diff file Expand all files Collapse all files

10
ktransformers/server/schemas/legacy/completions.py
View file

@ -1,17 +1,17 @@
from typing import List, Optional
from enum import Enum
from pydantic import BaseModel, Field
from ktransformers.server.config.config import Config
from ..base import Object
class CompletionCreate(BaseModel):
model: str
prompt: str | List[str]
stream: bool = False
temperature: Optional[float] = Field(default=0.6)
top_p: Optional[float] = Field(default=1)
max_tokens: Optional[int] = Field(default=50)
max_completion_tokens: Optional[int] = Field(default=50)
temperature: Optional[float] = Field(default=Config().temperature)
top_p: Optional[float] = Field(default=Config().top_p)
max_tokens: Optional[int] = Field(default=Config().max_new_tokens)
max_completion_tokens: Optional[int] = Field(default=Config().max_new_tokens)
def get_tokenizer_messages(self):
if isinstance(self.prompt,List):