
LMCache
Redis for LLMs
Stars: 680

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 | Official Email |
TL;DR - Redis for LLMs.
LMCache is a 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 reuse the KV caches of any reused text (not necessarily prefix) in any serving engine instance. Thus, LMCache saves precious GPU cycles and reduces response delay for users.
By combining LMCache with vLLM, LMCaches achieves 3-10x delay savings and GPU cycle reduction in many LLM use cases, including multi-round QA and RAG.
Try LMCache with pre-built vllm docker images here.
Please refer to our detailed documentation for LMCache V1 and LMCache V0
Fill out the interest form and our team will reach out to you! https://forms.gle/mQfQDUXbKfp2St1z7
- [x] LMCache V1 with vLLM integration with following features is live 🔥
- High performance CPU KVCache offloading
- Disaggregated prefill
- P2P KVCache sharing
- [x] LMCache is supported in the vLLM production stack ecosystem
- [x] User and developer documentation
- [x] Stable support for non-prefix KV caches
- [x] Support installation through pip install and integrate with latest vLLM
- [x] First release of LMCache
Our latest blog posts and the documentation pages are available online
The community meeting for LMCache is co-hosted with the community meeting for the vLLM production stack project.
Meeting Details:
-
Tuesdays at 4:00 PM PT – Add to Calendar
-
Tuesdays at 8:00 AM PT – Add to Calendar
Meetings alternate weekly between the two times. All are welcome to join!
We welcome and value any contributions and collaborations. Please check out CONTRIBUTING.md for how to get involved.
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}
}
@article{yao2024cacheblend,
title={CacheBlend: Fast Large Language Model Serving with Cached Knowledge Fusion},
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},
journal={arXiv preprint arXiv:2405.16444},
year={2024}
}
This project 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.

ReaLHF
ReaLHF is a distributed system designed for efficient RLHF training with Large Language Models (LLMs). It introduces a novel approach called parameter reallocation to dynamically redistribute LLM parameters across the cluster, optimizing allocations and parallelism for each computation workload. ReaL minimizes redundant communication while maximizing GPU utilization, achieving significantly higher Proximal Policy Optimization (PPO) training throughput compared to other systems. It supports large-scale training with various parallelism strategies and enables memory-efficient training with parameter and optimizer offloading. The system seamlessly integrates with HuggingFace checkpoints and inference frameworks, allowing for easy launching of local or distributed experiments. ReaLHF offers flexibility through versatile configuration customization and supports various RLHF algorithms, including DPO, PPO, RAFT, and more, while allowing the addition of custom algorithms for high efficiency.

agentsociety
AgentSociety is an advanced framework designed for building agents in urban simulation environments. It integrates LLMs' planning, memory, and reasoning capabilities to generate realistic behaviors. The framework supports dataset-based, text-based, and rule-based environments with interactive visualization. It includes tools for interviews, surveys, interventions, and metric recording tailored for social experimentation.

Slow_Thinking_with_LLMs
STILL is an open-source project exploring slow-thinking reasoning systems, focusing on o1-like reasoning systems. The project has released technical reports on enhancing LLM reasoning with reward-guided tree search algorithms and implementing slow-thinking reasoning systems using an imitate, explore, and self-improve framework. The project aims to replicate the capabilities of industry-level reasoning systems by fine-tuning reasoning models with long-form thought data and iteratively refining training datasets.

nixtla
Nixtla is a production-ready generative pretrained transformer for time series forecasting and anomaly detection. It can accurately predict various domains such as retail, electricity, finance, and IoT with just a few lines of code. TimeGPT introduces a paradigm shift with its standout performance, efficiency, and simplicity, making it accessible even to users with minimal coding experience. The model is based on self-attention and is independently trained on a vast time series dataset to minimize forecasting error. It offers features like zero-shot inference, fine-tuning, API access, adding exogenous variables, multiple series forecasting, custom loss function, cross-validation, prediction intervals, and handling irregular timestamps.

DocsGPT
DocsGPT is an open-source documentation assistant powered by GPT models. It simplifies the process of searching for information in project documentation by allowing developers to ask questions and receive accurate answers. With DocsGPT, users can say goodbye to manual searches and quickly find the information they need. The tool aims to revolutionize project documentation experiences and offers features like live previews, Discord community, guides, and contribution opportunities. It consists of a Flask app, Chrome extension, similarity search index creation script, and a frontend built with Vite and React. Users can quickly get started with DocsGPT by following the provided setup instructions and can contribute to its development by following the guidelines in the CONTRIBUTING.md file. The project follows a Code of Conduct to ensure a harassment-free community environment for all participants. DocsGPT is licensed under MIT and is built with LangChain.

ktransformers
KTransformers is a flexible Python-centric framework designed to enhance the user's experience with advanced kernel optimizations and placement/parallelism strategies for Transformers. It provides a Transformers-compatible interface, RESTful APIs compliant with OpenAI and Ollama, and a simplified ChatGPT-like web UI. The framework aims to serve as a platform for experimenting with innovative LLM inference optimizations, focusing on local deployments constrained by limited resources and supporting heterogeneous computing opportunities like GPU/CPU offloading of quantized models.

llm-course
The LLM course is divided into three parts: 1. 🧩 **LLM Fundamentals** covers essential knowledge about mathematics, Python, and neural networks. 2. 🧑🔬 **The LLM Scientist** focuses on building the best possible LLMs using the latest techniques. 3. 👷 **The LLM Engineer** focuses on creating LLM-based applications and deploying them. For an interactive version of this course, I created two **LLM assistants** that will answer questions and test your knowledge in a personalized way: * 🤗 **HuggingChat Assistant**: Free version using Mixtral-8x7B. * 🤖 **ChatGPT Assistant**: Requires a premium account. ## 📝 Notebooks A list of notebooks and articles related to large language models. ### Tools | Notebook | Description | Notebook | |----------|-------------|----------| | 🧐 LLM AutoEval | Automatically evaluate your LLMs using RunPod |  | | 🥱 LazyMergekit | Easily merge models using MergeKit in one click. |  | | 🦎 LazyAxolotl | Fine-tune models in the cloud using Axolotl in one click. |  | | ⚡ AutoQuant | Quantize LLMs in GGUF, GPTQ, EXL2, AWQ, and HQQ formats in one click. |  | | 🌳 Model Family Tree | Visualize the family tree of merged models. |  | | 🚀 ZeroSpace | Automatically create a Gradio chat interface using a free ZeroGPU. |  |

agentUniverse
agentUniverse is a framework for developing applications powered by multi-agent based on large language model. It provides essential components for building single agent and multi-agent collaboration mechanism for customizing collaboration patterns. Developers can easily construct multi-agent applications and share pattern practices from different fields. The framework includes pre-installed collaboration patterns like PEER and DOE for complex task breakdown and data-intensive tasks.

deepflow
DeepFlow is an open-source project that provides deep observability for complex cloud-native and AI applications. It offers Zero Code data collection with eBPF for metrics, distributed tracing, request logs, and function profiling. DeepFlow is integrated with SmartEncoding to achieve Full Stack correlation and efficient access to all observability data. With DeepFlow, cloud-native and AI applications automatically gain deep observability, removing the burden of developers continually instrumenting code and providing monitoring and diagnostic capabilities covering everything from code to infrastructure for DevOps/SRE teams.

HuixiangDou2
HuixiangDou2 is a robustly optimized GraphRAG approach that integrates multiple open-source projects to improve performance in graph-based augmented generation. It conducts comparative experiments and achieves a significant score increase, leading to a GraphRAG implementation with recognized performance. The repository provides code improvements, dense retrieval for querying entities and relationships, real domain knowledge testing, and impact analysis on accuracy.

MME-RealWorld
MME-RealWorld is a benchmark designed to address real-world applications with practical relevance, featuring 13,366 high-resolution images and 29,429 annotations across 43 tasks. It aims to provide substantial recognition challenges and overcome common barriers in existing Multimodal Large Language Model benchmarks, such as small data scale, restricted data quality, and insufficient task difficulty. The dataset offers advantages in data scale, data quality, task difficulty, and real-world utility compared to existing benchmarks. It also includes a Chinese version with additional images and QA pairs focused on Chinese scenarios.

higress
Higress is an open-source cloud-native API gateway built on the core of Istio and Envoy, based on Alibaba's internal practice of Envoy Gateway. It is designed for AI-native API gateway, serving AI businesses such as Tongyi Qianwen APP, Bailian Big Model API, and Machine Learning PAI platform. Higress provides capabilities to interface with LLM model vendors, AI observability, multi-model load balancing/fallback, AI token flow control, and AI caching. It offers features for AI gateway, Kubernetes Ingress gateway, microservices gateway, and security protection gateway, with advantages in production-level scalability, stream processing, extensibility, and ease of use.

MMStar
MMStar is an elite vision-indispensable multi-modal benchmark comprising 1,500 challenge samples meticulously selected by humans. It addresses two key issues in current LLM evaluation: the unnecessary use of visual content in many samples and the existence of unintentional data leakage in LLM and LVLM training. MMStar evaluates 6 core capabilities across 18 detailed axes, ensuring a balanced distribution of samples across all dimensions.

trafilatura
Trafilatura is a Python package and command-line tool for gathering text on the Web and simplifying the process of turning raw HTML into structured, meaningful data. It includes components for web crawling, downloads, scraping, and extraction of main texts, metadata, and comments. The tool aims to focus on actual content, avoid noise, and make sense of data and metadata. It is robust, fast, and widely used by companies and institutions. Trafilatura outperforms other libraries in text extraction benchmarks and offers various features like support for sitemaps, parallel processing, configurable extraction of key elements, multiple output formats, and optional add-ons. The tool is actively maintained with regular updates and comprehensive documentation.
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.