Awesome
Parrot: Efficient Serving of LLM-based Application with Semantic Variables
This project is a research prototype for now. Being eargerly iterated.
Install
See INSTALL.md for installation instructions.
Run Parrot
Run the Compose Script in a Single Machine
We provide some one-click scripts to run Parrot in a single machine with sample configs. You can check them in the sample_configs/launch
folder.
bash sample_configs/launch/launch_single_vicuna_13b.sh
<!-- **Run Docker Compose in a Cluster**
TODO -->
Start a ServeCore Server
You can separately start a ServeCore server.
python3 -m parrot.serve.http_server --config_path <config_path>
Start an Engine Server
You can separately start an engine server. If you choose to connect to the ServeCore server, you need to start the ServeCore server first and specify the ServeCore server address in the config file.
python3 -m parrot.engine.http_server --config_path <config_path>
Contributing
This project welcomes contributions and suggestions. Most contributions require you to agree to a Contributor License Agreement (CLA) declaring that you have the right to, and actually do, grant us the rights to use your contribution. For details, visit https://cla.opensource.microsoft.com.
When you submit a pull request, a CLA bot will automatically determine whether you need to provide a CLA and decorate the PR appropriately (e.g., status check, comment). Simply follow the instructions provided by the bot. You will only need to do this once across all repos using our CLA.
This project has adopted the Microsoft Open Source Code of Conduct. For more information see the Code of Conduct FAQ or contact opencode@microsoft.com with any additional questions or comments.
Trademarks
This project may contain trademarks or logos for projects, products, or services. Authorized use of Microsoft trademarks or logos is subject to and must follow Microsoft's Trademark & Brand Guidelines. Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship. Any use of third-party trademarks or logos are subject to those third-party's policies.