Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-06-29T14:11:24.646931Z
Paper Citation Record · LEDGER
As of 21 August 2026, this Paper Citation Record lists 13 of 13 outbound references and 3 inbound Pith citation observations for arXiv:2605.28302.
A citation records a reference. It does not transfer a finding from one paper to another.
Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-06-29T14:11:24.646931Z
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-21T06:32:19.484+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-08-15T14:42:38.994773Z
A source-named dated measurement, never combined with another source.
Source: pith, observed 2026-07-11T01:57:50.965515Z
13 of 13 outbound references displayed
External citation measurements
No source-named external measurement is stored.
Observation eed0d6e2-6f1f-4ac5-abb2-b116cc224555 · outbound
How Far Can Disaggregation Go? A Design-Space Exploration of Attention-FFN Disaggregation for Efficient MoE LLM Serving SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills
Reference 1
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 4b85e23f-3e5c-49f5-809e-1a56ba95cf1c · outbound
How Far Can Disaggregation Go? A Design-Space Exploration of Attention-FFN Disaggregation for Efficient MoE LLM Serving Vidur: A Large-Scale Simulation Framework For LLM Inference
Reference 2
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation d7d3be51-3dc0-445c-be18-c542eccbef34 · outbound
How Far Can Disaggregation Go? A Design-Space Exploration of Attention-FFN Disaggregation for Efficient MoE LLM Serving MIST: A Co-Design Framework for Heterogeneous, Multi-Stage LLM Inference
Reference 3
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 1cf17043-136e-4f42-ad74-5b81a772a514 · outbound
How Far Can Disaggregation Go? A Design-Space Exploration of Attention-FFN Disaggregation for Efficient MoE LLM Serving DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
Reference 4
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation ace63582-4a37-4169-a2c8-4a4cad7c4011 · outbound
How Far Can Disaggregation Go? A Design-Space Exploration of Attention-FFN Disaggregation for Efficient MoE LLM Serving Efficient Memory Management for Large Language Model Serving with PagedAttention , booktitle =
Reference 5
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 5c764205-8eb9-4e84-a64a-2d0bba678963 · outbound
How Far Can Disaggregation Go? A Design-Space Exploration of Attention-FFN Disaggregation for Efficient MoE LLM Serving Unresolved cited work
Reference 6
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c212e841-e076-4b5d-addc-3e3296d96e53 · outbound
How Far Can Disaggregation Go? A Design-Space Exploration of Attention-FFN Disaggregation for Efficient MoE LLM Serving [Online; accessed 2025-04-11]
Reference 7
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b2be4053-d887-480c-84cb-8bd442695509 · outbound
How Far Can Disaggregation Go? A Design-Space Exploration of Attention-FFN Disaggregation for Efficient MoE LLM Serving Unresolved cited work
Reference 8
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d0936738-e468-426e-8201-4c02bcb7e291 · outbound
How Far Can Disaggregation Go? A Design-Space Exploration of Attention-FFN Disaggregation for Efficient MoE LLM Serving StepMesh: A high-performance, low-latency communication library for attention-ffn disaggregation, 2025.https://github.com/stepfun-ai/StepMesh
Reference 9
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 607b2d92-25c1-41b5-93a1-caf608414d34 · outbound
How Far Can Disaggregation Go? A Design-Space Exploration of Attention-FFN Disaggregation for Efficient MoE LLM Serving AIConfigurator: Lightning-fast configuration optimization for multi-framework LLM serv- ing
Reference 10
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation b3685467-e4ef-4344-996b-a59f74b5c1de · outbound
How Far Can Disaggregation Go? A Design-Space Exploration of Attention-FFN Disaggregation for Efficient MoE LLM Serving MegaScale-Infer: Serving Mixture-of-Experts at Scale with Disaggregated Expert Parallelism
Reference 11
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 19344009-4e15-4d56-b87a-6b608318d107 · outbound
How Far Can Disaggregation Go? A Design-Space Exploration of Attention-FFN Disaggregation for Efficient MoE LLM Serving The prototype is used for correctness and implementation guidance, while the cluster-scale results use measured backend costs and AstraSim communication modeling
Reference 12
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 49e46e87-8c24-4c0e-b9d4-63cda2b8e306 · outbound
How Far Can Disaggregation Go? A Design-Space Exploration of Attention-FFN Disaggregation for Efficient MoE LLM Serving In (a), KV transfers cross the node boundary; in (b), each prefill–decode pair shares a node
Reference 13
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b4250cbf-f3e2-4ed9-946d-6dd6324ac619 · inbound
Think Before You Grid-Search: Floor-First Triage for LLM Serving How Far Can Disaggregation Go? A Design-Space Exploration of Attention-FFN Disaggregation for Efficient MoE LLM Serving
Reference 38
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 85f7eb06-7a9b-4bf2-b48e-7ca6860e30a4 · inbound
Think Before You Grid-Search: Floor-First Triage for LLM Serving How Far Can Disaggregation Go? A Design-Space Exploration of Attention-FFN Disaggregation for Efficient MoE LLM Serving
Reference 38
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.
Observation 14580223-7cfd-4f10-8900-4bf0fd3148dc · inbound
AFD-Ledger: Deployment Provisioning for Attention--FFN Disaggregation How Far Can Disaggregation Go? A Design-Space Exploration of Attention-FFN Disaggregation for Efficient MoE LLM Serving
Reference 35
Source-reported events for the cited work
Unavailable: canonical work link unavailable.