FastDeploy

RuntimesPythonApache-2.0★ 3.7k
GitHub ↗

FastDeploy is a PaddlePaddle-based inference and deployment toolkit for LLMs and VLMs, offering OpenAI-compatible serving, PD disaggregation

Runtime
Runs
LLM and VLM inference and serving
Hardware
NVIDIA GPU, Kunlunxin XPU, Hygon DCU, Iluvatar GPU, Enflame GCU, MetaX GPU, Intel Gaudi
API
OpenAI API, vLLM-compatible

Other tools that do the same work

Agent stacks with this tool(1)View graph