
LMCache
Supercharge Your LLM with the Fastest KV Cache Layer
Stars: 5372

LMCache is a serving engine extension designed to reduce time to first token (TTFT) and increase throughput, particularly in long-context scenarios. It stores key-value caches of reusable texts across different locations like GPU, CPU DRAM, and Local Disk, allowing the reuse of any text in any serving engine instance. By combining LMCache with vLLM, significant delay savings and GPU cycle reduction are achieved in various large language model (LLM) use cases, such as multi-round question answering and retrieval-augmented generation (RAG). LMCache provides integration with the latest vLLM version, offering both online serving and offline inference capabilities. It supports sharing key-value caches across multiple vLLM instances and aims to provide stable support for non-prefix key-value caches along with user and developer documentation.
README:
| Blog | Documentation | Join Slack | Interest Form | Roadmap
🔥 NEW: For enterprise-scale deployment of LMCache and vLLM, please check out vLLM Production Stack. LMCache is also officially supported in llm-d and KServe!
LMCache is an LLM serving engine extension to reduce TTFT and increase throughput, especially under long-context scenarios. By storing the KV caches of reusable texts across various locations, including (GPU, CPU DRAM, Local Disk), LMCache reuses the KV caches of any reused text (not necessarily prefix) in any serving engine instance. Thus, LMCache saves precious GPU cycles and reduces user response delay.
By combining LMCache with vLLM, developers achieve 3-10x delay savings and GPU cycle reduction in many LLM use cases, including multi-round QA and RAG.
- [x] 🔥 Integration with vLLM v1 with the following features:
- High performance CPU KVCache offloading
- Disaggregated prefill
- P2P KVCache sharing
- [x] LMCache is supported in the vLLM production stack, llm-d, and KServe
- [x] Stable support for non-prefix KV caches
- [x] Storage support as follows:
- CPU
- Disk
- NIXL
- [x] Installation support through pip and latest vLLM
To use LMCache, simply install lmcache
from your package manager, e.g. pip:
pip install lmcache
Works on Linux NVIDIA GPU platform.
More detailed installation instructions are available in the docs, particularly if you are not using the latest stable version of vllm or using another serving engine with different dependencies. Any "undefined symbol" or torch mismatch versions can be resolved in the documentation.
The best way to get started is to checkout the Quickstart Examples in the docs.
Check out the LMCache documentation which is available online.
We also post regularly in LMCache blogs.
Go hands-on with our examples, demonstrating how to address different use cases with LMCache.
Fill out the interest form, sign up for our newsletter, join LMCache slack, check out LMCache website, or drop an email, and our team will reach out to you!
The community meeting for LMCache is hosted bi-weekly. All are welcome to join!
Meetings are held bi-weekly on: Tuesdays at 9:00 AM PT – Add to Calendar
We keep notes from each meeting on this document for summaries of standups, discussion, and action items.
Recordings of meetings are available on the YouTube LMCache channel.
We welcome and value all contributions and collaborations. Please check out Contributing Guide on how to contribute.
We continually update [Onboarding] Welcoming contributors with good first issues!
If you use LMCache for your research, please cite our papers:
@inproceedings{liu2024cachegen,
title={Cachegen: Kv cache compression and streaming for fast large language model serving},
author={Liu, Yuhan and Li, Hanchen and Cheng, Yihua and Ray, Siddhant and Huang, Yuyang and Zhang, Qizheng and Du, Kuntai and Yao, Jiayi and Lu, Shan and Ananthanarayanan, Ganesh and others},
booktitle={Proceedings of the ACM SIGCOMM 2024 Conference},
pages={38--56},
year={2024}
}
@article{cheng2024large,
title={Do Large Language Models Need a Content Delivery Network?},
author={Cheng, Yihua and Du, Kuntai and Yao, Jiayi and Jiang, Junchen},
journal={arXiv preprint arXiv:2409.13761},
year={2024}
}
@inproceedings{10.1145/3689031.3696098,
author = {Yao, Jiayi and Li, Hanchen and Liu, Yuhan and Ray, Siddhant and Cheng, Yihua and Zhang, Qizheng and Du, Kuntai and Lu, Shan and Jiang, Junchen},
title = {CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusion},
year = {2025},
url = {https://doi.org/10.1145/3689031.3696098},
doi = {10.1145/3689031.3696098},
booktitle = {Proceedings of the Twentieth European Conference on Computer Systems},
pages = {94–109},
}
The LMCache codebase is licensed under Apache License 2.0. See the LICENSE file for details.
For Tasks:
Click tags to check more tools for each tasksFor Jobs:
Alternative AI tools for LMCache
Similar Open Source Tools

LMCache
LMCache is a serving engine extension designed to reduce time to first token (TTFT) and increase throughput, particularly in long-context scenarios. It stores key-value caches of reusable texts across different locations like GPU, CPU DRAM, and Local Disk, allowing the reuse of any text in any serving engine instance. By combining LMCache with vLLM, significant delay savings and GPU cycle reduction are achieved in various large language model (LLM) use cases, such as multi-round question answering and retrieval-augmented generation (RAG). LMCache provides integration with the latest vLLM version, offering both online serving and offline inference capabilities. It supports sharing key-value caches across multiple vLLM instances and aims to provide stable support for non-prefix key-value caches along with user and developer documentation.

clearml
ClearML is an auto-magical suite of tools designed to streamline AI workflows. It includes modules for experiment management, MLOps/LLMOps, data management, model serving, and more. ClearML offers features like experiment tracking, model serving, orchestration, and automation. It supports various ML/DL frameworks and integrates with Jupyter Notebook and PyCharm for remote debugging. ClearML aims to simplify collaboration, automate processes, and enhance visibility in AI projects.

clearml
ClearML is a suite of tools designed to streamline the machine learning workflow. It includes an experiment manager, MLOps/LLMOps, data management, and model serving capabilities. ClearML is open-source and offers a free tier hosting option. It supports various ML/DL frameworks and integrates with Jupyter Notebook and PyCharm. ClearML provides extensive logging capabilities, including source control info, execution environment, hyper-parameters, and experiment outputs. It also offers automation features, such as remote job execution and pipeline creation. ClearML is designed to be easy to integrate, requiring only two lines of code to add to existing scripts. It aims to improve collaboration, visibility, and data transparency within ML teams.

aiida-core
AiiDA (www.aiida.net) is a workflow manager for computational science with a strong focus on provenance, performance and extensibility. **Features** * **Workflows:** Write complex, auto-documenting workflows in python, linked to arbitrary executables on local and remote computers. The event-based workflow engine supports tens of thousands of processes per hour with full checkpointing. * **Data provenance:** Automatically track inputs, outputs & metadata of all calculations in a provenance graph for full reproducibility. Perform fast queries on graphs containing millions of nodes. * **HPC interface:** Move your calculations to a different computer by changing one line of code. AiiDA is compatible with schedulers like SLURM, PBS Pro, torque, SGE or LSF out of the box. * **Plugin interface:** Extend AiiDA with plugins for new simulation codes (input generation & parsing), data types, schedulers, transport modes and more. * **Open Science:** Export subsets of your provenance graph and share them with peers or make them available online for everyone on the Materials Cloud. * **Open source:** AiiDA is released under the MIT open source license

mlflow
MLflow is a platform to streamline machine learning development, including tracking experiments, packaging code into reproducible runs, and sharing and deploying models. MLflow offers a set of lightweight APIs that can be used with any existing machine learning application or library (TensorFlow, PyTorch, XGBoost, etc), wherever you currently run ML code (e.g. in notebooks, standalone applications or the cloud). MLflow's current components are:
* `MLflow Tracking

docling
Docling simplifies document processing, parsing diverse formats including advanced PDF understanding, and providing seamless integrations with the general AI ecosystem. It offers features such as parsing multiple document formats, advanced PDF understanding, unified DoclingDocument representation format, various export formats, local execution capabilities, plug-and-play integrations with agentic AI tools, extensive OCR support, and a simple CLI. Coming soon features include metadata extraction, visual language models, chart understanding, and complex chemistry understanding. Docling is installed via pip and works on macOS, Linux, and Windows environments. It provides detailed documentation, examples, integrations with popular frameworks, and support through the discussion section. The codebase is under the MIT license and has been developed by IBM.

docling
Docling is a tool that bundles PDF document conversion to JSON and Markdown in an easy, self-contained package. It can convert any PDF document to JSON or Markdown format, understand detailed page layout, reading order, recover table structures, extract metadata such as title, authors, references, and language, and optionally apply OCR for scanned PDFs. The tool is designed to be stable, lightning fast, and suitable for macOS and Linux environments.

DataDreamer
DataDreamer is a powerful open-source Python library designed for prompting, synthetic data generation, and training workflows. It is simple, efficient, and research-grade, allowing users to create prompting workflows, generate synthetic datasets, and train models with ease. The library is built for researchers, by researchers, focusing on correctness, best practices, and reproducibility. It offers features like aggressive caching, resumability, support for bleeding-edge techniques, and easy sharing of datasets and models. DataDreamer enables users to run multi-step prompting workflows, generate synthetic datasets for various tasks, and train models by aligning, fine-tuning, instruction-tuning, and distilling them using existing or synthetic data.

SillyTavern
SillyTavern is a user interface you can install on your computer (and Android phones) that allows you to interact with text generation AIs and chat/roleplay with characters you or the community create. SillyTavern is a fork of TavernAI 1.2.8 which is under more active development and has added many major features. At this point, they can be thought of as completely independent programs.

MONAI
MONAI is a PyTorch-based, open-source framework for deep learning in healthcare imaging. It provides a comprehensive set of tools for medical image analysis, including data preprocessing, model training, and evaluation. MONAI is designed to be flexible and easy to use, making it a valuable resource for researchers and developers in the field of medical imaging.

sealos
Sealos is a cloud operating system distribution based on the Kubernetes kernel, designed for a seamless development lifecycle. It allows users to spin up full-stack environments in seconds, effortlessly push releases, and scale production seamlessly. With core features like easy application management, quick database creation, and cloud universality, Sealos offers efficient and economical cloud management with high universality and ease of use. The platform also emphasizes agility and security through its multi-tenancy sharing model. Sealos is supported by a community offering full documentation, Discord support, and active development roadmap.

agentgateway
Agentgateway is an open source data plane optimized for agentic AI connectivity within or across any agent framework or environment. It provides drop-in security, observability, and governance for agent-to-agent and agent-to-tool communication, supporting leading interoperable protocols like Agent2Agent (A2A) and Model Context Protocol (MCP). Highly performant, security-first, multi-tenant, dynamic, and supporting legacy API transformation, agentgateway is designed to handle any scale and run anywhere with any agent framework.

Kiln
Kiln is an intuitive tool for fine-tuning LLM models, generating synthetic data, and collaborating on datasets. It offers desktop apps for Windows, MacOS, and Linux, zero-code fine-tuning for various models, interactive data generation, and Git-based version control. Users can easily collaborate with QA, PM, and subject matter experts, generate auto-prompts, and work with a wide range of models and providers. The tool is open-source, privacy-first, and supports structured data tasks in JSON format. Kiln is free to use and helps build high-quality AI products with datasets, facilitates collaboration between technical and non-technical teams, allows comparison of models and techniques without code, ensures structured data integrity, and prioritizes user privacy.

lightllm
LightLLM is a Python-based LLM (Large Language Model) inference and serving framework known for its lightweight design, scalability, and high-speed performance. It offers features like tri-process asynchronous collaboration, Nopad for efficient attention operations, dynamic batch scheduling, FlashAttention integration, tensor parallelism, Token Attention for zero memory waste, and Int8KV Cache. The tool supports various models like BLOOM, LLaMA, StarCoder, Qwen-7b, ChatGLM2-6b, Baichuan-7b, Baichuan2-7b, Baichuan2-13b, InternLM-7b, Yi-34b, Qwen-VL, Llava-7b, Mixtral, Stablelm, and MiniCPM. Users can deploy and query models using the provided server launch commands and interact with multimodal models like QWen-VL and Llava using specific queries and images.

StratosphereLinuxIPS
Slips is a powerful endpoint behavioral intrusion prevention and detection system that uses machine learning to detect malicious behaviors in network traffic. It can work with network traffic in real-time, PCAP files, and network flows from tools like Suricata, Zeek/Bro, and Argus. Slips threat detection is based on machine learning models, threat intelligence feeds, and expert heuristics. It gathers evidence of malicious behavior and triggers alerts when enough evidence is accumulated. The tool is Python-based and supported on Linux and MacOS, with blocking features only on Linux. Slips relies on Zeek network analysis framework and Redis for interprocess communication. It offers a graphical user interface for easy monitoring and analysis.

FAV0
FAV0 Weekly is a repository that records weekly updates on front-end, AI, and computer-related content. It provides light and dark mode switching, bilingual interface, RSS subscription function, Giscus comment system, high-definition image preview, font settings customization, and SEO optimization. Users can stay updated with the latest weekly releases by starring/watching the repository. The repository is dual-licensed under the MIT License and CC-BY-4.0 License.
For similar tasks

LMCache
LMCache is a serving engine extension designed to reduce time to first token (TTFT) and increase throughput, particularly in long-context scenarios. It stores key-value caches of reusable texts across different locations like GPU, CPU DRAM, and Local Disk, allowing the reuse of any text in any serving engine instance. By combining LMCache with vLLM, significant delay savings and GPU cycle reduction are achieved in various large language model (LLM) use cases, such as multi-round question answering and retrieval-augmented generation (RAG). LMCache provides integration with the latest vLLM version, offering both online serving and offline inference capabilities. It supports sharing key-value caches across multiple vLLM instances and aims to provide stable support for non-prefix key-value caches along with user and developer documentation.
For similar jobs

weave
Weave is a toolkit for developing Generative AI applications, built by Weights & Biases. With Weave, you can log and debug language model inputs, outputs, and traces; build rigorous, apples-to-apples evaluations for language model use cases; and organize all the information generated across the LLM workflow, from experimentation to evaluations to production. Weave aims to bring rigor, best-practices, and composability to the inherently experimental process of developing Generative AI software, without introducing cognitive overhead.

LLMStack
LLMStack is a no-code platform for building generative AI agents, workflows, and chatbots. It allows users to connect their own data, internal tools, and GPT-powered models without any coding experience. LLMStack can be deployed to the cloud or on-premise and can be accessed via HTTP API or triggered from Slack or Discord.

VisionCraft
The VisionCraft API is a free API for using over 100 different AI models. From images to sound.

kaito
Kaito is an operator that automates the AI/ML inference model deployment in a Kubernetes cluster. It manages large model files using container images, avoids tuning deployment parameters to fit GPU hardware by providing preset configurations, auto-provisions GPU nodes based on model requirements, and hosts large model images in the public Microsoft Container Registry (MCR) if the license allows. Using Kaito, the workflow of onboarding large AI inference models in Kubernetes is largely simplified.

PyRIT
PyRIT is an open access automation framework designed to empower security professionals and ML engineers to red team foundation models and their applications. It automates AI Red Teaming tasks to allow operators to focus on more complicated and time-consuming tasks and can also identify security harms such as misuse (e.g., malware generation, jailbreaking), and privacy harms (e.g., identity theft). The goal is to allow researchers to have a baseline of how well their model and entire inference pipeline is doing against different harm categories and to be able to compare that baseline to future iterations of their model. This allows them to have empirical data on how well their model is doing today, and detect any degradation of performance based on future improvements.

tabby
Tabby is a self-hosted AI coding assistant, offering an open-source and on-premises alternative to GitHub Copilot. It boasts several key features: * Self-contained, with no need for a DBMS or cloud service. * OpenAPI interface, easy to integrate with existing infrastructure (e.g Cloud IDE). * Supports consumer-grade GPUs.

spear
SPEAR (Simulator for Photorealistic Embodied AI Research) is a powerful tool for training embodied agents. It features 300 unique virtual indoor environments with 2,566 unique rooms and 17,234 unique objects that can be manipulated individually. Each environment is designed by a professional artist and features detailed geometry, photorealistic materials, and a unique floor plan and object layout. SPEAR is implemented as Unreal Engine assets and provides an OpenAI Gym interface for interacting with the environments via Python.

Magick
Magick is a groundbreaking visual AIDE (Artificial Intelligence Development Environment) for no-code data pipelines and multimodal agents. Magick can connect to other services and comes with nodes and templates well-suited for intelligent agents, chatbots, complex reasoning systems and realistic characters.