Paper Citation Record · LEDGER

Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving

As of 6 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 45 inbound Pith citation observations for arXiv:2407.00079.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2407.00079 v4

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 45 of 45 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-06T06:34:29.942622+00:00

measured 45 of 45 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T18:11:15.969489Z

measured 1 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: pith, observed 2026-08-05T02:28:24.338817Z

Reference resolution

0 of 0 outbound references displayed

verified exact0
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

13
pith, observed 2026-08-05T02:28:24.338817Z

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation 352b9913-3e7c-4066-8ad5-660f610f4814 · inbound

RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval cites this paper.

RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving

Reference 105

Resolution: verified exact; arxiv_id, observed 2026-05-18T08:12:02.005662Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 7528d19c-e4e7-4b6a-b19b-c5c1cff684c4 · inbound

BatchLLM: Optimizing Large Batched LLM Inference with Global Prefix Sharing and Throughput-oriented Token Batching cites this paper.

BatchLLM: Optimizing Large Batched LLM Inference with Global Prefix Sharing and Throughput-oriented Token Batching Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-05-23T16:58:11.891568Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 1597fe2b-4566-4862-95e8-7fe26d69ce6c · inbound

Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Model cites this paper.

Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Model Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving

Reference 38

Resolution: verified exact; arxiv_id, observed 2026-05-19T08:02:23.720450Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation b0771189-3fea-4e80-91d1-60c3bcb1ea70 · inbound

From Human Memory to AI Memory: A Survey on Memory Mechanisms in the Era of LLMs cites this paper.

From Human Memory to AI Memory: A Survey on Memory Mechanisms in the Era of LLMs Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving

Reference 121

Resolution: verified exact; arxiv_id, observed 2026-05-17T11:05:09.843818Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 3a129b94-c23c-47d6-b7e9-d5193030acaa · inbound

Cache Your Prompt When It's Green: Carbon-Aware Caching for Large Language Model Serving cites this paper.

Cache Your Prompt When It's Green: Carbon-Aware Caching for Large Language Model Serving Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving

Reference 64

Resolution: verified exact; arxiv_id, observed 2026-05-19T13:17:18.476761Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 9ebb2090-66ea-44ff-9cb0-72c5a1ba1f84 · inbound

On Evaluating Performance of LLM Inference Serving Systems cites this paper.

On Evaluating Performance of LLM Inference Serving Systems Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-06T18:11:15.969489Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2fe5dd24-aa07-44fe-8361-135161d09c58 · inbound

Past-Future Scheduler for LLM Serving under SLA Guarantees cites this paper.

Past-Future Scheduler for LLM Serving under SLA Guarantees Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-06T17:46:20.294435Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42bc596e-6c1b-4d5c-90ba-f02346f3abcd · inbound

IAM: Efficient Inference through Attention Mapping between Different-scale LLMs cites this paper.

IAM: Efficient Inference through Attention Mapping between Different-scale LLMs Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-06T17:06:33.971861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e423ebc-4e6b-4f56-876d-b671ecf41ed6 · inbound

Sandwich: Joint Configuration Search and Hot-Switching for Efficient CPU LLM Serving cites this paper.

Sandwich: Joint Configuration Search and Hot-Switching for Efficient CPU LLM Serving Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving

Reference 49

Resolution: verified exact; arxiv_id, observed 2026-05-22T15:11:43.902548Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 0e7aad83-de96-4a2d-a74d-e8aea9d126dd · inbound

HFX: Joint Design of Algorithms and Systems for Multi-SLO Serving and Fast Scaling cites this paper.

HFX: Joint Design of Algorithms and Systems for Multi-SLO Serving and Fast Scaling Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving

Reference 33

Resolution: verified exact; arxiv_id, observed 2026-05-18T21:41:51.752300Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 92be0001-d2d4-4b27-b8bb-b84232124710 · inbound

Taming the Chaos: Coordinated Autoscaling for Heterogeneous and Disaggregated LLM Inference cites this paper.

Taming the Chaos: Coordinated Autoscaling for Heterogeneous and Disaggregated LLM Inference Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-05T15:45:38.950601Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 259df76e-5863-4d72-8fd7-f6bd7ca33955 · inbound

TokenCake: A KV-Cache-centric Serving Framework for LLM-based Multi-Agent Applications cites this paper.

TokenCake: A KV-Cache-centric Serving Framework for LLM-based Multi-Agent Applications Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-21T21:20:38.741005Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 358e0bb5-b56f-4ab7-91df-b8ce2596b5a0 · inbound

Tree Training: Accelerating Agentic LLMs Training via Shared Prefix Reuse cites this paper.

Tree Training: Accelerating Agentic LLMs Training via Shared Prefix Reuse Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving

Reference 12

Resolution: metadata mismatch; arxiv_id, observed 2026-05-18T02:05:39.054797Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation a9981e83-bb93-4c9b-b8c6-f65b2d426fc6 · inbound

The Workload-Router-Pool Architecture for LLM Inference Optimization: A Vision Paper from the vLLM Semantic Router Project cites this paper.

The Workload-Router-Pool Architecture for LLM Inference Optimization: A Vision Paper from the vLLM Semantic Router Project Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving

Reference 64

Resolution: verified exact; arxiv_id, observed 2026-05-15T06:45:12.282525Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 2c786606-936f-41f7-9486-acba5244a115 · inbound

JoyAI-LLM Flash: Advancing Mid-Scale LLMs with Token Efficiency cites this paper.

JoyAI-LLM Flash: Advancing Mid-Scale LLMs with Token Efficiency Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving

Reference 97

Resolution: verified exact; arxiv_id, observed 2026-05-13T19:28:09.832457Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation be385161-c75d-4823-ac03-f1f4d621b35d · inbound

MemExplorer: Navigating the Heterogeneous Memory Design Space for Agentic Inference NPUs cites this paper.

MemExplorer: Navigating the Heterogeneous Memory Design Space for Agentic Inference NPUs Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving

Reference 45

Resolution: verified exact; arxiv_id, observed 2026-05-10T07:47:12.427852Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 1324798b-10f5-435d-887e-e830606d2d60 · inbound

Salca: A Sparsity-Aware Hardware Accelerator for Efficient Long-Context Attention Decoding cites this paper.

Salca: A Sparsity-Aware Hardware Accelerator for Efficient Long-Context Attention Decoding Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving

Reference 39

Resolution: verified exact; arxiv_id, observed 2026-05-11T23:11:18.872688Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation ce4ab281-2187-4221-b962-1aa18009bdbf · inbound

Predictive Multi-Tier Memory Management for KV Cache in Large-Scale GPU Inference cites this paper.

Predictive Multi-Tier Memory Management for KV Cache in Large-Scale GPU Inference Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-05-10T10:14:10.662004Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 72ce4e52-8721-4738-a326-af124bf4f46b · inbound

Tutti: Making SSD-Backed KV Cache Practical for Long-Context LLM Serving cites this paper.

Tutti: Making SSD-Backed KV Cache Practical for Long-Context LLM Serving Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving

Reference 40

Resolution: verified exact; arxiv_id, observed 2026-05-11T16:31:10.413581Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 0c86b6ee-87f1-4c9d-9069-54b6c96603dc · inbound

PreFT: Prefill-only finetuning for efficient inference cites this paper.

PreFT: Prefill-only finetuning for efficient inference Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving

Reference 33

Resolution: verified exact; arxiv_id, observed 2026-05-15T02:13:30.631370Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation f6e62323-3a28-47cb-85f4-a532990b95b5 · inbound

Model-Native Computing Architecture: Envisioning Future System Architecture Through the Lens of Computer Architecture cites this paper.

Model-Native Computing Architecture: Envisioning Future System Architecture Through the Lens of Computer Architecture Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving

Reference 128

Resolution: verified exact; arxiv_id, observed 2026-07-01T19:36:09.325179Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 87eee698-7063-4fc6-a4ec-335ac8a4eaf7 · inbound

Idleness is Relative: Exploiting Tool-Call Idle Windows for Offloading in Agentic Systems with MORI cites this paper.

Idleness is Relative: Exploiting Tool-Call Idle Windows for Offloading in Agentic Systems with MORI Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving

Reference 45

Resolution: verified exact; arxiv_id, observed 2026-07-01T21:06:13.602230Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation da99d0d7-d3d8-4dc5-96d0-80e2439e0af0 · inbound

Vortex: Efficient and Programmable Sparse Attention Serving for AI Agents cites this paper.

Vortex: Efficient and Programmable Sparse Attention Serving for AI Agents Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-07-02T13:36:59.446547Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation b99726db-bcc4-451a-a747-db9dd14c3604 · inbound

Semantic Cache Distillation: Efficient State Transfer via Reuse and Selective Patching cites this paper.

Semantic Cache Distillation: Efficient State Transfer via Reuse and Selective Patching Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving

Reference 50

Resolution: verified exact; arxiv_id, observed 2026-07-02T16:27:09.081015Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 6a7026a3-6fad-4535-9b78-648b29be30b2 · inbound

SpectrumKV: Per-Token Mixed-Precision KV Cache Transfer for Prefill-Decode Disaggregated LLM Serving cites this paper.

SpectrumKV: Per-Token Mixed-Precision KV Cache Transfer for Prefill-Decode Disaggregated LLM Serving Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-07-02T22:27:26.298208Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation e304f344-56ad-4675-bbe0-9395700334cb · inbound

Beyond Per-Token Pricing: A Concurrency-Aware Methodology for LLM Infrastructure Cost Estimation cites this paper.

Beyond Per-Token Pricing: A Concurrency-Aware Methodology for LLM Infrastructure Cost Estimation Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving

Reference 31

Resolution: verified exact; arxiv_id, observed 2026-07-03T12:48:11.785527Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation ef0ee4aa-1e77-4571-83ad-aee61d130932 · inbound

Token-Operations-Oriented Inference Optimization Techniques for Large Models cites this paper.

Token-Operations-Oriented Inference Optimization Techniques for Large Models Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving

Reference 176

Resolution: verified exact; arxiv_id, observed 2026-07-04T05:09:36.750859Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation a1bed497-9edd-4dc1-a395-b959a7092a3d · inbound

Token-Operations-Oriented Inference Optimization Techniques for Large Models cites this paper.

Token-Operations-Oriented Inference Optimization Techniques for Large Models Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving

Reference 176

Resolution: unresolved; no resolver link, observed 2026-08-02T10:49:19.644055Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96d4f8d0-d408-420f-aa10-6104605c5c63 · inbound

Human-Less LLM Serving: Quantifying the Human Tax on Throughput cites this paper.

Human-Less LLM Serving: Quantifying the Human Tax on Throughput Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-07-01T00:45:11.798434Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation b1e392b9-f9d0-46e6-ac5c-b3c2d2f25b59 · inbound

Demystifying the Design Space and Best Practices for Heterogeneous LLM Inference and Serving cites this paper.

Demystifying the Design Space and Best Practices for Heterogeneous LLM Inference and Serving Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-06-30T14:04:45.338293Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 1d063ebc-92c8-4e23-a621-98eefecb3671 · inbound

Demystifying the Design Space and Best Practices for Heterogeneous LLM Inference and Serving cites this paper.

Demystifying the Design Space and Best Practices for Heterogeneous LLM Inference and Serving Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-07-01T08:55:35.140206Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 50f5c434-9115-4a2f-b9d4-92fe427608c8 · inbound

Omni-Flow: A Unified Workflow Orchestration and Distributed KV Cache Sharing Framework for Multimodal Inference cites this paper.

Omni-Flow: A Unified Workflow Orchestration and Distributed KV Cache Sharing Framework for Multimodal Inference Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving

Reference 11

Resolution: metadata mismatch; arxiv_id, observed 2026-07-01T11:35:43.612928Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation f2898e7b-bcdb-45b4-8c5e-0560faa4ad5a · inbound

ELDR: Expert-Locality-Aware Decode Routing for PD-Disaggregated MoE Serving cites this paper.

ELDR: Expert-Locality-Aware Decode Routing for PD-Disaggregated MoE Serving Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving

Reference 31

Resolution: verified exact; arxiv_id, observed 2026-07-02T06:56:43.946753Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 69825baa-86d1-4130-823e-eadfc4c44395 · inbound

ELDR: Expert-Locality-Aware Decode Routing for PD-Disaggregated MoE Serving cites this paper.

ELDR: Expert-Locality-Aware Decode Routing for PD-Disaggregated MoE Serving Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving

Reference 31

Resolution: verified exact; arxiv_id, observed 2026-07-03T18:58:50.500809Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 36bbb44a-af48-4c3d-9700-7d0f15b55344 · inbound

OmniPilot: An Uncertainty-Aware LLM Inference Advisor for Heterogeneous GPU Clusters cites this paper.

OmniPilot: An Uncertainty-Aware LLM Inference Advisor for Heterogeneous GPU Clusters Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-07-03T06:37:42.198474Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation d8b16788-b522-4b7e-ab51-38379c76484a · inbound

CoCoScale: Leveraging Layer-wise Scaling to Unlock the Potential of Online LLM Serving cites this paper.

CoCoScale: Leveraging Layer-wise Scaling to Unlock the Potential of Online LLM Serving Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving

Reference 25

Resolution: unresolved; no resolver link, observed 2026-07-11T21:08:24.159706Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b019a78b-e277-413a-8f33-392ccf9cb36d · inbound

Think Before You Grid-Search: Floor-First Triage for LLM Serving cites this paper.

Think Before You Grid-Search: Floor-First Triage for LLM Serving Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-07-08T22:45:40.129136Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation bdbfc038-faf2-431a-afd8-67b23139ec73 · inbound

Think Before You Grid-Search: Floor-First Triage for LLM Serving cites this paper.

Think Before You Grid-Search: Floor-First Triage for LLM Serving Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-07-11T01:57:51.505587Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation d36af72a-b138-47a3-8cc6-7be560f40b68 · inbound

FreqDepthKV: Frequency-Guided Depth Sharing for Robust KV Cache Compression in Long-Context LLM Inference cites this paper.

FreqDepthKV: Frequency-Guided Depth Sharing for Robust KV Cache Compression in Long-Context LLM Inference Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving

Reference 103

Resolution: verified exact; local_arxiv, observed 2026-07-11T00:17:45.637015Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 6a9d0331-1118-4278-9fc4-43b1397b7ba6 · inbound

DepthWeave-KV: Token-Adaptive Cross-Layer Residual Factorization for Long-Context KV Cache Compression cites this paper.

DepthWeave-KV: Token-Adaptive Cross-Layer Residual Factorization for Long-Context KV Cache Compression Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving

Reference 117

Resolution: verified exact; local_arxiv, observed 2026-07-08T03:14:31.493985Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation b2f41ac6-904f-47b6-9e19-4a5677ee4d3c · inbound

What to Keep, What to Forget: A Rate--Distortion View of Memory Compaction in LLMs and Agents cites this paper.

What to Keep, What to Forget: A Rate--Distortion View of Memory Compaction in LLMs and Agents Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving

Reference 96

Resolution: verified exact; local_arxiv, observed 2026-07-10T01:36:44.325524Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 43c055a7-a8eb-4daf-8c8d-f31ee9ecee5d · inbound

Towards Efficient Large Language Model Serving: A Survey on System-Aware KV Cache Optimization cites this paper.

Towards Efficient Large Language Model Serving: A Survey on System-Aware KV Cache Optimization Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving

Reference 8

Resolution: metadata mismatch; local_arxiv, observed 2026-07-10T00:56:40.960364Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 2f6ad3a4-c991-4d54-9e5d-9ccff413a265 · inbound

Accelerating GPU Inference of Large Language Models with Moderately Unstructured Sparse Weight Matrices cites this paper.

Accelerating GPU Inference of Large Language Models with Moderately Unstructured Sparse Weight Matrices Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving

Reference 24

Resolution: unresolved; no resolver link, observed 2026-07-13T07:32:31.866525Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e5e8596-d161-4b47-ab91-067c04b95cb9 · inbound

Topology-Aware Data Movement for Disaggregated GPU Inference cites this paper.

Topology-Aware Data Movement for Disaggregated GPU Inference Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-03T00:55:34.428229Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ed69102-1abf-4a82-988c-ccbeda51369b · inbound

Spatial Prefix Caching for Wireless Edge LLM Inference: A Stochastic-Geometry and Queueing Framework cites this paper.

Spatial Prefix Caching for Wireless Edge LLM Inference: A Stochastic-Geometry and Queueing Framework Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-06T00:33:26.100297Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.