ai-dynamo /
dynamo
A Datacenter Scale Distributed Inference Serving Framework
Updated 37 min ago
Why now
Version v1.6.1 came out on October 27.
+40 stars gained this week
Stars gained each day, last 30 days
Usual pace · 8 / day
Oct 4Oct 19Today
This week Before Usual pace
In short
Aimed at teams serving LLMs across several GPUs or nodes, it sits above SGLang, TensorRT-LLM or vLLM and needs Kubernetes-style infrastructure to coordinate them. It is not useful for a single model on one GPU.
Summary written by AI from the repository’s description and README.
ai-dynamo / dynamo
View on GitHub(opens in new tab)