Installation#
Setup using Python#
Prerequisites#
OS: Linux
Python: 3.10 – 3.12
GPU: NVIDIA compute capability 7.0+ (e.g., V100, T4, RTX20xx, A100, L4, H100, etc.)
CUDA 12.8+
Note
LMCache does not support Windows natively. To run LMCache on Windows, you can use the Windows Subsystem for Linux (WSL) with a compatible Linux distribution, or use some community-maintained forks.
Install Stable LMCache from PyPI#
The simplest way to install the latest stable release of LMCache is through PyPI:
pipinstalllmcache
Install Latest LMCache from TestPyPI#
These wheels are continually built from the latest LMCache source code (not officially stable release).
pipinstall--index-urlhttps://pypi.org/simple--extra-index-urlhttps://test.pypi.org/simplelmcache==0.2.2.dev57
See the latest pre-release of LMCache:latest LMCache pre-releases and replace0.2.2.dev57 with the latest pre-release version.
This will install all dependencies from the real PyPI and only LMCache itself from TestPyPI.
Confirm that you have the latest pre-release:
python>>>importlmcache>>>fromimportlib.metadataimportversion>>>print(version("lmcache"))0.2.2.dev57# should be the latest pre-release version you installed
Install Latest LMCache from Source#
To install from source, clone the repository and install in editable mode:
gitclonehttps://github.com/LMCache/LMCache.gitcdLMCachepipinstall-e.
Install LMCache with uv#
We recommend developers to useuv for a better package management:
gitclonehttps://github.com/LMCache/LMCache.gitcdLMCacheuvvenv--python3.12source.venv/bin/activateuvpipinstall-e.
LMCache with vLLM v1#
LMCache is integrated with the latest vLLM (vLLM v1). To use it, install the latest vLLM package:
pipinstallvllm
Test whether LMCache works with vLLM v1 by running:
python3-c"import vllm.distributed.kv_transfer.kv_connector.v1.lmcache_connector"
LMCache with vLLM v0#
Note
LMCache is also integrated with vLLM v0. Refer tothe example in vLLM.See theexamples README to understand how to run the script for vLLM v0.
Setup using Docker#
Prerequisites#
Docker Engine 27.0+
Pre-built LMCache integrated with vLLM Images#
We provide pre-built container images of LMCache integrated with vLLM.
You can get the latest stable image as follows:
dockerpulllmcache/vllm-openai
You can get the nightly build of latest code of LMcache and vLLM as follows:
dockerpulllmcache/vllm-openai:latest-nightly