This repository has been archived on 2024-10-27. You can view files and clone it, but cannot push or open issues or pull requests.
local-llm-server/llm_server/llm/generator.py

16 lines
559 B
Python

from llm_server import opts
from llm_server.cluster.cluster_config import cluster_config
def generator(request_json_body, cluster_backend, timeout: int = None):
mode = cluster_config.get_backend(cluster_backend)['mode']
if mode == 'ooba':
# from .oobabooga.generate import generate
# return generate(request_json_body)
raise NotImplementedError
elif mode == 'vllm':
from .vllm.generate import generate
return generate(request_json_body, cluster_backend, timeout=timeout)
else:
raise Exception