Linkredibles
← Back to discover

llm-d Router

An intelligent inference router for LLM traffic with load-aware and cache-aware routing.

The Linkredibles take

Why it's worth knowing.

Optimize inference traffic using model, load, cache, and scheduling signals.

Topics

#llm#inference#routing#kubernetes#gpu#performance

Open source repository

Explore the source behind llm-d Router.

Read the source, explore the project, and see how it is being developed on GitHub.

Visit repository↗

Keep exploring

You might also like.

Browse all projects →