Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links
Paper Citation Record · LEDGER
MegaScale-Infer: Serving Mixture-of-Experts at Scale with Disaggregated Expert Parallelism
As of 4 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 20 inbound Pith citation observations for arXiv:2504.02263.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-04T06:34:03.388597+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-08-01T21:09:11.364229Z
A source-named dated measurement, never combined with another source.
Source: pith, observed 2026-07-11T01:57:51.799355Z
Reference resolution
0 of 0 outbound references displayed
- verified exact0
- verified fuzzy0
- unresolved0
- parse uncertain0
- malformed identifier0
- metadata mismatch0
External citation measurements
No source-named external measurement is stored.
Outbound references
No outbound reference observations are available for this paper version.
Pith citing papers
Observation 4170b967-3868-4c85-a98c-236bd462ed3e · inbound
Patterns behind Chaos: Forecasting Data Movement for Efficient Large-Scale MoE LLM Inference cites this paper.
Patterns behind Chaos: Forecasting Data Movement for Efficient Large-Scale MoE LLM Inference MegaScale-Infer: Serving Mixture-of-Experts at Scale with Disaggregated Expert Parallelism
Reference 82
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-18T09:56:13.351360Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 7848e185-d250-47a8-8a66-a8eb1782ec6b · inbound
Understanding and Improving Communication Performance in Multi-node LLM Inference cites this paper.
Understanding and Improving Communication Performance in Multi-node LLM Inference MegaScale-Infer: Serving Mixture-of-Experts at Scale with Disaggregated Expert Parallelism
Reference 20
- Resolution
- verified exact
- arxiv_id, observed 2026-05-21T19:25:31.170511Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation c4c876eb-e875-4d31-ac8e-fcd684833a36 · inbound
CascadeInfer: Length-Aware Scheduling of LLM Serving with Low Latency and Load Balancing cites this paper.
CascadeInfer: Length-Aware Scheduling of LLM Serving with Low Latency and Load Balancing MegaScale-Infer: Serving Mixture-of-Experts at Scale with Disaggregated Expert Parallelism
Reference 38
- Resolution
- verified exact
- arxiv_id, observed 2026-05-21T17:25:25.306024Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 2b3a3e2f-cceb-4c60-b5fd-5b4c88afa7d3 · inbound
Analytical Provisioning for Attention-FFN Disaggregated LLM Serving under Stochastic Workloads cites this paper.
Analytical Provisioning for Attention-FFN Disaggregated LLM Serving under Stochastic Workloads MegaScale-Infer: Serving Mixture-of-Experts at Scale with Disaggregated Expert Parallelism
Reference 14
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-16T09:57:43.044677Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 5ccfd899-b6aa-43a5-874e-954b84295ffe · inbound
UniEP: Unified Expert-Parallel MoE MegaKernel for LLM Training cites this paper.
UniEP: Unified Expert-Parallel MoE MegaKernel for LLM Training MegaScale-Infer: Serving Mixture-of-Experts at Scale with Disaggregated Expert Parallelism
Reference 53
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-11T13:06:05.120260Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 565bb87d-36bd-4662-b50b-1bfbd99a8a33 · inbound
AMMA: A Multi-Chiplet Memory-Centric Architecture for Low-Latency 1M Context Attention Serving cites this paper.
AMMA: A Multi-Chiplet Memory-Centric Architecture for Low-Latency 1M Context Attention Serving MegaScale-Infer: Serving Mixture-of-Experts at Scale with Disaggregated Expert Parallelism
Reference 73
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T00:46:13.103672Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation bb301088-de0b-452e-b328-17b1de5a17ad · inbound
Position: LLM Serving Needs Mathematical Optimization and Algorithmic Foundations, Not Just Heuristics cites this paper.
Position: LLM Serving Needs Mathematical Optimization and Algorithmic Foundations, Not Just Heuristics MegaScale-Infer: Serving Mixture-of-Experts at Scale with Disaggregated Expert Parallelism
Reference 12
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-11T16:01:20.442803Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 61a6d518-c87d-4f57-918b-37c3b66ffddb · inbound
Surviving Partial Rank Failures in Wide Expert-Parallel MoE Inference cites this paper.
Surviving Partial Rank Failures in Wide Expert-Parallel MoE Inference MegaScale-Infer: Serving Mixture-of-Experts at Scale with Disaggregated Expert Parallelism
Reference 35
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T06:11:24.750960Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 503f1b1f-4b25-41c8-a928-54e506617e8d · inbound
DisagMoE: Computation-Communication overlapped MoE Training via Disaggregated AF-Pipe Parallelism cites this paper.
DisagMoE: Computation-Communication overlapped MoE Training via Disaggregated AF-Pipe Parallelism MegaScale-Infer: Serving Mixture-of-Experts at Scale with Disaggregated Expert Parallelism
Reference 35
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-13T01:52:06.223867Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 520a18fa-c1e0-47ae-b153-7176647fd42b · inbound
Sieve: Dynamic Expert-Aware PIM Acceleration for Evolving Mixture-of-Experts Models cites this paper.
Sieve: Dynamic Expert-Aware PIM Acceleration for Evolving Mixture-of-Experts Models MegaScale-Infer: Serving Mixture-of-Experts at Scale with Disaggregated Expert Parallelism
Reference 61
- Resolution
- verified exact
- arxiv_id, observed 2026-05-13T00:57:00.557004Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation fb7b79ee-4de6-40ab-9305-8a3f4c92eaf7 · inbound
Frontier: Towards Comprehensive and Accurate LLM Inference Simulation cites this paper.
Frontier: Towards Comprehensive and Accurate LLM Inference Simulation MegaScale-Infer: Serving Mixture-of-Experts at Scale with Disaggregated Expert Parallelism
Reference 55
- Resolution
- verified exact
- arxiv_id, observed 2026-05-21T03:49:31.087613Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation b3685467-e4ef-4344-996b-a59f74b5c1de · inbound
How Far Can Disaggregation Go? A Design-Space Exploration of Attention-FFN Disaggregation for Efficient MoE LLM Serving cites this paper.
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
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-06-29T14:13:29.982788Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 9258a694-17f4-49b9-8639-79b68b12b46d · inbound
ViBE: Co-Optimizing Workload Skew and Hardware Variability for MoE Serving cites this paper.
ViBE: Co-Optimizing Workload Skew and Hardware Variability for MoE Serving MegaScale-Infer: Serving Mixture-of-Experts at Scale with Disaggregated Expert Parallelism
Reference 51
- Resolution
- verified exact
- arxiv_id, observed 2026-07-01T20:46:13.234967Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation b7a52402-1472-4cb6-9520-55da65adaea6 · inbound
KernelFlume: Elastic Core-Attention Scaling for Agentic Long-Context Decoding cites this paper.
KernelFlume: Elastic Core-Attention Scaling for Agentic Long-Context Decoding MegaScale-Infer: Serving Mixture-of-Experts at Scale with Disaggregated Expert Parallelism
Reference 45
- Resolution
- verified exact
- arxiv_id, observed 2026-06-30T03:04:14.249359Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 45bb04f7-a1e5-4bdb-b14c-388ef21ab2da · inbound
SmoothAgent: Efficient Long-Horizon LLM-Based Agent Serving with Lookahead Context Engineering cites this paper.
SmoothAgent: Efficient Long-Horizon LLM-Based Agent Serving with Lookahead Context Engineering MegaScale-Infer: Serving Mixture-of-Experts at Scale with Disaggregated Expert Parallelism
Reference 88
- Resolution
- verified exact
- arxiv_id, observed 2026-07-02T17:27:14.635873Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 670587ad-d936-4cf8-8301-8e930c18c1ad · 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 MegaScale-Infer: Serving Mixture-of-Experts at Scale with Disaggregated Expert Parallelism
Reference 49
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-08T22:45:40.136686Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 187d20aa-2255-457a-a9f0-0beef80ae805 · 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 MegaScale-Infer: Serving Mixture-of-Experts at Scale with Disaggregated Expert Parallelism
Reference 49
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-11T01:57:51.823762Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 75c2e5bf-2501-4702-8692-52378c91b852 · inbound
UBEP: Re-architecting Expert Parallelism Communication Library for Production Superpods cites this paper.
UBEP: Re-architecting Expert Parallelism Communication Library for Production Superpods MegaScale-Infer: Serving Mixture-of-Experts at Scale with Disaggregated Expert Parallelism
Reference 58
- Resolution
- verified exact
- local_arxiv, observed 2026-07-08T13:44:54.956949Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 371f47ea-b64a-4420-b4c4-ea85b525c0df · inbound
UBEP: Re-architecting Expert Parallelism Communication Library for Production Superpods cites this paper.
UBEP: Re-architecting Expert Parallelism Communication Library for Production Superpods MegaScale-Infer: Serving Mixture-of-Experts at Scale with Disaggregated Expert Parallelism
Reference 58
- Resolution
- verified exact
- local_arxiv, observed 2026-07-11T01:07:44.166561Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation f02061f2-9310-4fc9-b34b-2ff7c2ba9e14 · inbound
PagedWeight: Efficient MoE LLM Serving with Dynamic Quality-Aware Weight Quantization cites this paper.
PagedWeight: Efficient MoE LLM Serving with Dynamic Quality-Aware Weight Quantization MegaScale-Infer: Serving Mixture-of-Experts at Scale with Disaggregated Expert Parallelism
Reference 35
- Resolution
- unresolved
- no resolver link, observed 2026-08-01T21:09:11.364229Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.