11 KiB
Welcome to Mooncake
:::{figure} ./image/mooncake-icon.png :align: center :alt: Mooncake :class: no-scaled-link :width: 60% :::
:::{raw} html
A KVCache-centric Disaggregated Architecture for LLM Serving.
:::Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI. Now both the Transfer Engine and Mooncake Store are open-sourced! This repository also hosts its technical report and the open-sourced traces.
🎉 Overview
Mooncake features a KVCache-centric disaggregated architecture that separates prefill and decode clusters. It also leverages underutilized CPU, DRAM, and SSD resources in GPU clusters to build a disaggregated KVCache pool.
:::{figure} ./image/architecture.png :align: center :alt: Mooncake architecture :width: 88% :::
At the center of Mooncake is a KVCache-centric scheduler that balances effective throughput with latency-related Service Level Objectives (SLOs). In highly overloaded scenarios, Mooncake uses prediction-based early rejection to avoid wasting computation on requests that cannot meet their SLOs. Experiments show that Mooncake is especially effective for long-context workloads, achieving up to a 525% throughput increase in simulated scenarios while meeting SLOs. Under real workloads, Mooncake's architecture enables Kimi to handle 75% more requests.
🔄 Updates
- May 7, 2026: 🚀 vLLM officially features Mooncake Store — a deep dive into how Mooncake's distributed KVCache engine supercharges vLLM inference with high-throughput, memory-efficient, cross-instance KV cache sharing!
- Apr 29, 2026: SGLang introduces RDMA-based P2P weight transfer for large-scale distributed RL using Mooncake TransferEngine, achieving 7x faster weight updates for the 1T-parameter Kimi-K2 model (53s → 7.2s) with zero-copy RDMA transfer across thousands of GPUs.
- Mar 19, 2026: TorchSpec: Speculative Decoding Training at Scale is open sourced, using Mooncake to decouple inference and training via efficient hidden states management.
- Mar 5, 2026: LightX2V now supports disaggregated deployment based on Mooncake, enabling encoder/transformer service decoupling with Mooncake Transfer Engine for high-performance cross-device and cross-machine data transfer.
- Feb 25, 2026: SGLang merged Encoder Global Cache Manager, introducing a Mooncake-powered global multimodal embedding cache that enables cross-instance sharing of ViT embeddings to avoid redundant GPU computation.
:::{dropdown} More :animate: fade-in
- Feb 24, 2026: vLLM-Omni introduces disaggregated inference connectors with support for both
MooncakeStoreConnectorandMooncakeTransferEngineConnectorfor multi-node omni-modality pipelines. - Feb 12, 2026: Mooncake Joins PyTorch Ecosystem We are thrilled to announce that Mooncake has officially joined the PyTorch Ecosystem!
- Jan 28, 2026: FlexKV, a distributed KV store and cache system from Tencent and NVIDIA in collaboration with the community, now supports distributed KVCache reuse with the Mooncake Transfer Engine.
- Dec 27, 2025: Collaboration with ROLL! Check out the paper here.
- Dec 23, 2025: SGLang introduces Encode-Prefill-Decode (EPD) Disaggregation with Mooncake as a transfer backend. This integration allows decoupling compute-intensive multimodal encoders (e.g., Vision Transformers) from language model nodes, utilizing Mooncake's RDMA engine for zero-copy transfer of large multimodal embeddings.
- Dec 19, 2025: Mooncake Transfer Engine has been integrated into TensorRT LLM for KVCache transfer in PD-disaggregated inference.
- Dec 19, 2025: Mooncake Transfer Engine has been directly integrated into vLLM v1 as a KV Connector in PD-disaggregated setups.
- Nov 07, 2025: RBG + SGLang HiCache + Mooncake, a role-based out-of-the-box solution for cloud native deployment, which is elastic, scalable, and high-performance.
- Sept 18, 2025: Mooncake Store empowers vLLM Ascend by serving as the distributed KV cache pool backend.
- Sept 10, 2025: SGLang officially supports Mooncake Store as a hierarchical KV caching storage backend. The integration extends RadixAttention with multi-tier KV cache storage across device, host, and remote storage layers.
- Sept 10, 2025: The official & high-performance version of Mooncake P2P Store is open-sourced as checkpoint-engine. It has been successfully applied in K1.5 and K2 production training, updating Kimi-K2 model (1T parameters) across thousands of GPUs in ~20s.
- Aug 23, 2025: xLLM high-performance inference engine builds hybrid KV cache management based on Mooncake, supporting global KV cache management with intelligent offloading and prefetching.
- Aug 18, 2025: vLLM-Ascend integrates Mooncake Transfer Engine for KV cache register and disaggregate prefill, enabling efficient distributed inference on Ascend NPUs.
- Jul 20, 2025: Mooncake powers the deployment of Kimi K2 on 128 H200 GPUs with PD disaggregation and large-scale expert parallelism, achieving 224k tokens/sec prefill throughput and 288k tokens/sec decode throughput.
- Jun 20, 2025: Mooncake becomes a PD disaggregation backend for LMDeploy.
- May 9, 2025: NIXL officially supports Mooncake Transfer Engine as a backend plugin.
- May 8, 2025: Mooncake x LMCache unite to pioneer KVCache-centric LLM serving system.
- May 5, 2025: Supported by Mooncake Team, SGLang release guidance to deploy DeepSeek with PD Disaggregation on 96 H100 GPUs.
- Apr 22, 2025: LMCache officially supports Mooncake Store as a remote connector.
- Apr 10, 2025: SGLang officially supports Mooncake Transfer Engine for disaggregated prefilling and KV cache transfer.
- Mar 7, 2025: We open-sourced the Mooncake Store, a distributed KVCache based on Transfer Engine. vLLM's xPyD disaggregated prefilling & decoding based on Mooncake Store will be released soon.
- Feb 25, 2025: Mooncake receives the Best Paper Award at FAST 2025!
- Feb 21, 2025: The updated traces used in our FAST'25 paper have been released.
- Dec 16, 2024: vLLM officially supports Mooncake Transfer Engine for disaggregated prefilling and KV cache transfer.
- Nov 28, 2024: We open-sourced the Transfer Engine, the central component of Mooncake. We also provide two demonstrations of Transfer Engine: a P2P Store and vLLM integration.
- July 9, 2024: We open-sourced the trace as a JSONL file.
- June 27, 2024: We present a series of Chinese blogs with more discussions on zhihu 1, 2, 3, 4, 5, 6, 7.
- June 26, 2024: Initial technical report release.
:::
Documentation
% How to start using Mooncake?
:::{toctree} :caption: Getting Started :maxdepth: 2
getting_started/build getting_started/quick-start
:::
% Deployment docs
:::{toctree} :caption: Deployment :maxdepth: 2
deployment/mooncake-store-deployment-guide getting_started/examples/sglang-integration/index getting_started/examples/vllm-integration/index Mooncake x LMCache Integration<getting_started/examples/lmcache-integration> Mooncake x LMDeploy Integration<getting_started/examples/lmdeploy-integration-v0.9> :::
% Making the most out of Mooncake
:::{toctree} :caption: Performance :maxdepth: 1
performance/vllm/index performance/sglang/index performance/mooncake/index :::
% Explanation of Mooncake internals
:::{toctree} :caption: Design Documents :maxdepth: 2
design/architecture design/mooncake-store design/p2p-store design/transfer-engine/index design/hicache-design design/engram design/unified-parallel-tensor-io design/tent/overview design/tent/tebench design/conductor/conductor-architecture-design :::
% API Documentation
:::{toctree} :caption: API Reference :maxdepth: 2
api-reference/python/index api-reference/cpp/index api-reference/http/index :::
% Q&A for Mooncake
:::{toctree} :caption: Troubleshooting :maxdepth: 1
troubleshooting/error-code troubleshooting/troubleshooting :::
% Community
:::{toctree} :caption: Community :maxdepth: 1
community/governance :::
% Archived content
:::{toctree} :caption: Archived :maxdepth: 1
getting_started/examples/vllm-integration/vllm-mooncakestoreconnector getting_started/examples/vllm-integration/vllm-integration-v0.2 getting_started/examples/vllm-integration/vllm-integration-v0.3 getting_started/examples/vllm-integration/vllm-integration-v1.0 :::