Skip to content

⌘ K

Getting Started

3 Min Quick Example: Docker + Speedup with vLLM
Installation Guide
Docker Installation
Quickstart

Configure LMCache

LMCache v1
- Configuring LMCache v1
LMCache v0
- Configuring LMCache v0

Detailed Examples

LMCache v1
LMCache v0

Models

Supported Models

Developer Documentation

LMCache Overview
LMCache Engine Interface
LMCache GPU Connector Interface
LMCache Memory Object
LMCache Memory Interface
LMCache Backend Interface

Advanced

KV Blending
KVCache Evictor
vLLM Integration

/

LMCache v0

LMCache v0#

v0 Examples

Selecting a backend
Usage
- How to:
Saving the decode cache
- How to:
KV blending
- How to:

P2P KV Cache Sharing

Selecting a backend

© 2024, The LMCache Team Built with Sphinx 7.4.7