Repositories list
22 repositories
- A lightweight, configurable, and real-time simulator designed to mimic the behavior of vLLM without the need for GPUs or running actual heavy models.
- Achieve state of the art inference performance with modern accelerators on Kubernetes
- llm-d benchmark scripts and tooling
- llm-d Router: The intelligent entry point for inference requests
- Distributed KV cache scheduling & offloading libraries
- Website for llm-d: This repository builds the website seen at llm-d.ai
- Incubating P/D sidecar for llm-d
- Helm charts for llm-d
- Simplified model deployment on llm-d
ProTip! When viewing an organization's repositories, you can use the
props. filter to filter by custom property.