latest

• 升级vllm版本

• 支持GLM4和QWEN2系列模型

latest

some fix

latest

api-for-open-llm-v1.0.3

Fix embedding truncation

api-for-open-llm-v1.0.2

• Add support for llama-cpp-python

• Add DeepSeek, Yi template

• Refactor project

api-for-open-llm-v1.0.1

fix bug

api-for-open-llm-v1.0.0

openai>=1.2.0

api-for-open-llm-v0.0.5

master分支

openai<=0.28.0

api-for-open-llm-v0.0.4

• Update streamlit demo

• Add support for repetition penalty

• Add support for baichuan2 models

api-for-open-llm-v0.0.3

Update vllm arguments

api-for-open-llm-v0.0.2

• 启动方式参数改为设置环境变量

• 修改 api 代码结构