Paper Citation Record · LEDGER

DuetServe: Harmonizing Prefill and Decode for LLM Serving via Adaptive GPU Multiplexing

As of 4 August 2026, this Paper Citation Record lists 19 of 19 outbound references and 1 inbound Pith citation observation for arXiv:2511.04791.

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

pith.paper-citation-record.v1
2511.04791 v2

Coverage vector

measured 19 of 19 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-03T23:39:08.036454Z

measured 20 of 20 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-04T06:34:03.388597+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-28T04:57:08.746551Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-02T10:46:52.298443Z

Reference resolution

19 of 19 outbound references displayed

verified exact1
verified fuzzy0
unresolved18
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation faee7694-f5fa-4c23-aa26-734461bdc49e · outbound

This paper cites S., Ramjee, R., and Tumanov, A.

DuetServe: Harmonizing Prefill and Decode for LLM Serving via Adaptive GPU Multiplexing S., Ramjee, R., and Tumanov, A

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-03T23:39:05.344401Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d83e1e03-2924-46ef-9fb5-3cef716d1b72 · outbound

This paper cites ISBN 9798400712616.

DuetServe: Harmonizing Prefill and Decode for LLM Serving via Adaptive GPU Multiplexing ISBN 9798400712616

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-03T23:39:05.963627Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24997dbb-dafd-4851-83f9-d7a0965b0dc5 · outbound

This paper cites The Llama 3 Herd of Models.

DuetServe: Harmonizing Prefill and Decode for LLM Serving via Adaptive GPU Multiplexing The Llama 3 Herd of Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-03T23:39:06.217757Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae877024-34f8-43a3-9549-b818ea3d9c92 · outbound

This paper cites MemServe: Context Caching for Disaggregated LLM Serving with Elastic Memory Pool.

DuetServe: Harmonizing Prefill and Decode for LLM Serving via Adaptive GPU Multiplexing MemServe: Context Caching for Disaggregated LLM Serving with Elastic Memory Pool

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-03T23:39:06.591452Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a1e4f4d-6d0f-4b72-b764-30d9947e5e7d · outbound

This paper cites Bul- let: Boosting gpu utilization for llm serving via dy- namic spatial-temporal orchestration.arXiv preprint arXiv:2504.19516,.

DuetServe: Harmonizing Prefill and Decode for LLM Serving via Adaptive GPU Multiplexing Bul- let: Boosting gpu utilization for llm serving via dy- namic spatial-temporal orchestration.arXiv preprint arXiv:2504.19516,

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-03T23:39:06.693807Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b00b24c-47c9-44c4-a1ca-fceddc7379c9 · outbound

This paper cites Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models.

DuetServe: Harmonizing Prefill and Decode for LLM Serving via Adaptive GPU Multiplexing Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-03T23:39:06.769325Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89f5d42f-215a-4e1d-9c0e-7b0559827ac3 · outbound

This paper cites lmcache.ai/2025-04-29-pdbench/.

DuetServe: Harmonizing Prefill and Decode for LLM Serving via Adaptive GPU Multiplexing lmcache.ai/2025-04-29-pdbench/

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-03T23:39:06.882234Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34f30212-c926-4155-8db8-ba996fb96953 · outbound

This paper cites Azure llm inference trace 2023,.

DuetServe: Harmonizing Prefill and Decode for LLM Serving via Adaptive GPU Multiplexing Azure llm inference trace 2023,

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-03T23:39:07.099305Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 089141c0-e46f-48fa-a5c0-9d4bbdda9e17 · outbound

This paper cites GPT-4 Technical Report.

DuetServe: Harmonizing Prefill and Decode for LLM Serving via Adaptive GPU Multiplexing GPT-4 Technical Report

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-03T23:39:07.249012Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eed99aaf-864d-4c80-a05c-649a38a3c4f9 · outbound

This paper cites an unresolved cited work.

DuetServe: Harmonizing Prefill and Decode for LLM Serving via Adaptive GPU Multiplexing Unresolved cited work

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-03T23:39:07.384783Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9455ab2d-4938-4969-8633-9e880bf8a1ca · outbound

This paper cites Nexus:Proactive Intra-GPU Disaggregation of Prefill and Decode in LLM Serving.

DuetServe: Harmonizing Prefill and Decode for LLM Serving via Adaptive GPU Multiplexing Nexus:Proactive Intra-GPU Disaggregation of Prefill and Decode in LLM Serving

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-03T23:39:07.565606Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d4edeec-e363-4910-8dfb-0053f4fd3678 · outbound

This paper cites Cuda graphs compatibility of attention back- ends, 2025a.

DuetServe: Harmonizing Prefill and Decode for LLM Serving via Adaptive GPU Multiplexing Cuda graphs compatibility of attention back- ends, 2025a

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-03T23:39:07.694976Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 795a3d79-9edd-4103-9fbb-8ff49e53f522 · outbound

This paper cites Qwen3 Technical Report.

DuetServe: Harmonizing Prefill and Decode for LLM Serving via Adaptive GPU Multiplexing Qwen3 Technical Report

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-03T23:39:07.864886Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation badb81ca-3851-4295-8134-fad2b5dd08df · outbound

This paper cites Nanoflow: To- wards optimal large language model serving throughput.

DuetServe: Harmonizing Prefill and Decode for LLM Serving via Adaptive GPU Multiplexing Nanoflow: To- wards optimal large language model serving throughput

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-03T23:39:08.036454Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3558dd2f-fd35-4251-b89e-46968595aba2 · outbound

This paper cites ISBN 9781450381376.

DuetServe: Harmonizing Prefill and Decode for LLM Serving via Adaptive GPU Multiplexing ISBN 9781450381376

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-03T23:39:05.802487Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 633d21dc-2e09-4afa-a53e-f7dfe3ee0580 · outbound

This paper cites semi-PD: Towards Efficient LLM Serving via Phase-Wise Disaggregated Computation and Unified Storage.

DuetServe: Harmonizing Prefill and Decode for LLM Serving via Adaptive GPU Multiplexing semi-PD: Towards Efficient LLM Serving via Phase-Wise Disaggregated Computation and Unified Storage

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-03T23:39:06.362657Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d4d9977-53b8-4aba-a0ed-77fb97d7427d · outbound

This paper cites Optimizing slo- oriented llm serving with pd-multiplexing.arXiv preprint arXiv:2504.14489,.

DuetServe: Harmonizing Prefill and Decode for LLM Serving via Adaptive GPU Multiplexing Optimizing slo- oriented llm serving with pd-multiplexing.arXiv preprint arXiv:2504.14489,

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-03T23:39:05.625797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 990953a8-7b1d-4b14-a681-dbdbfbac60a4 · outbound

This paper cites Gemini: A Family of Highly Capable Multimodal Models.

DuetServe: Harmonizing Prefill and Decode for LLM Serving via Adaptive GPU Multiplexing Gemini: A Family of Highly Capable Multimodal Models

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-03T23:39:06.136972Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1e71ccb-e045-4960-9a4d-e425c2b5e784 · outbound

This paper cites Chow, M., Jahanshahi, A., and Wong, D.

DuetServe: Harmonizing Prefill and Decode for LLM Serving via Adaptive GPU Multiplexing Chow, M., Jahanshahi, A., and Wong, D

Reference 2025

Resolution: verified exact; doi, observed 2026-08-03T23:44:06.428629Z

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.

Pith citing papers

Observation 8c40914f-5fa0-4995-8bc9-b0d978ebdeeb · inbound

FlexNPU: Transparent NPU Virtualization for Dynamic LLM Prefill-Decode Co-location cites this paper.

FlexNPU: Transparent NPU Virtualization for Dynamic LLM Prefill-Decode Co-location DuetServe: Harmonizing Prefill and Decode for LLM Serving via Adaptive GPU Multiplexing

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-07-02T10:46:52.299777Z

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.