← Open Source
PaddlePaddle

FastDeploy

High-performance Inference and Deployment Toolkit for LLMs and VLMs based on PaddlePaddle

InfrastructureDeploy & ServeInference service optimizationPython
Open on GitHub
Momentum
+0stars in 24 hours0.0%
3.72k
Stars
757
Forks
+1
This week
100
Contributors
Created 2022-06-27 · Updated 2026-10-08 · #7038 today
Top developers