Paper Citation Record · LEDGER

PipeLive: Efficient Live In-place Pipeline Parallelism Reconfiguration for Dynamic LLM Serving

As of 15 August 2026, this Paper Citation Record lists 37 of 37 outbound references and 1 inbound Pith citation observation for arXiv:2604.12171.

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

pith.paper-citation-record.v1
2604.12171 v1

Coverage vector

measured 37 of 37 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-10T16:33:35.821999Z

measured 38 of 38 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-15T06:32:42.880941+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-26T19:32:31.882977Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-04T02:39:24.934173Z

Reference resolution

37 of 37 outbound references displayed

verified exact9
verified fuzzy12
unresolved16
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation aaef3e2c-75ad-42dc-8c7a-76bf0250021f · outbound

This paper cites Gulavani, Ramachandran Ramjee, and Alexey Tu- manov.

PipeLive: Efficient Live In-place Pipeline Parallelism Reconfiguration for Dynamic LLM Serving Gulavani, Ramachandran Ramjee, and Alexey Tu- manov

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T14:49:47.197850Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation cd26c68c-3870-4da7-bbb9-7a5bded63a30 · outbound

This paper cites Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al.

PipeLive: Efficient Live In-place Pipeline Parallelism Reconfiguration for Dynamic LLM Serving Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T14:49:47.211048Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 6b23ab1d-6236-4926-a289-397d830bab57 · outbound

This paper cites an unresolved cited work.

PipeLive: Efficient Live In-place Pipeline Parallelism Reconfiguration for Dynamic LLM Serving Unresolved cited work

Reference 3

Resolution: unresolved; raw_fallback, observed 2026-05-17T14:49:47.194514Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation aeea5955-1e7c-4810-8de7-9f64a479c4ff · outbound

This paper cites an unresolved cited work.

PipeLive: Efficient Live In-place Pipeline Parallelism Reconfiguration for Dynamic LLM Serving Unresolved cited work

Reference 4

Resolution: unresolved; raw_fallback, observed 2026-05-17T14:49:47.214953Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation e0f0b03e-7d69-47f4-b7df-c6ccd5c2bb7a · outbound

This paper cites Fu, Stefano Ermon, Atri Rudra, and Christopher Ré.

PipeLive: Efficient Live In-place Pipeline Parallelism Reconfiguration for Dynamic LLM Serving Fu, Stefano Ermon, Atri Rudra, and Christopher Ré

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T14:49:47.219374Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation b9052ce8-7cbb-4d64-97c8-40c4b4e14dea · outbound

This paper cites InAdvances in Neural Information Processing Systems (NeurIPS).

PipeLive: Efficient Live In-place Pipeline Parallelism Reconfiguration for Dynamic LLM Serving InAdvances in Neural Information Processing Systems (NeurIPS)

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T14:49:47.204826Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 2c0e0d56-fbf6-406c-9b2c-5a7da120d2d3 · outbound

This paper cites an unresolved cited work.

PipeLive: Efficient Live In-place Pipeline Parallelism Reconfiguration for Dynamic LLM Serving Unresolved cited work

Reference 7

Resolution: unresolved; raw_fallback, observed 2026-05-17T14:49:47.201322Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation c62b426f-d3c7-4c51-8da1-08d5256b163f · outbound

This paper cites The Llama 3 Herd of Models.

PipeLive: Efficient Live In-place Pipeline Parallelism Reconfiguration for Dynamic LLM Serving The Llama 3 Herd of Models

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-05-11T08:40:59.311909Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 9f024742-6abb-4e2d-92a6-a634314d7a49 · outbound

This paper cites M\'elange: Cost Efficient Large Language Model Serving by Exploiting GPU Heterogeneity.

PipeLive: Efficient Live In-place Pipeline Parallelism Reconfiguration for Dynamic LLM Serving M\'elange: Cost Efficient Large Language Model Serving by Exploiting GPU Heterogeneity

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-11T08:40:59.322868Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 44b8adc2-b72b-4782-8e0f-cea26d7a1431 · outbound

This paper cites an unresolved cited work.

PipeLive: Efficient Live In-place Pipeline Parallelism Reconfiguration for Dynamic LLM Serving Unresolved cited work

Reference 10

Resolution: unresolved; raw_fallback, observed 2026-05-17T14:49:47.207777Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 053f1ff8-6c06-4199-9e51-482fba29a010 · outbound

This paper cites an unresolved cited work.

PipeLive: Efficient Live In-place Pipeline Parallelism Reconfiguration for Dynamic LLM Serving Unresolved cited work

Reference 11

Resolution: unresolved; raw_fallback, observed 2026-05-17T14:49:47.122878Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 7aecad72-90e5-49fa-bb13-99b32a99a2e1 · outbound

This paper cites Le, Yonghui Wu, and Zhifeng Chen.

PipeLive: Efficient Live In-place Pipeline Parallelism Reconfiguration for Dynamic LLM Serving Le, Yonghui Wu, and Zhifeng Chen

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T14:49:47.159618Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 2d9f149d-13aa-4fa0-9dd6-10ad0cea0d41 · outbound

This paper cites an unresolved cited work.

PipeLive: Efficient Live In-place Pipeline Parallelism Reconfiguration for Dynamic LLM Serving Unresolved cited work

Reference 13

Resolution: unresolved; raw_fallback, observed 2026-05-17T14:49:47.165812Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 3dae9ef9-e34b-4771-8668-2ee25b79ff18 · outbound

This paper cites InProceedings of the 29th Symposium on Operating Systems Principles (SOSP ’23).

PipeLive: Efficient Live In-place Pipeline Parallelism Reconfiguration for Dynamic LLM Serving InProceedings of the 29th Symposium on Operating Systems Principles (SOSP ’23)

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T14:49:47.148063Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation b0ad49e0-2b45-4a6e-a3a3-23195e7f6a4d · outbound

This paper cites FlexPipe: Adapting Dynamic LLM Serving Through Inflight Pipeline Refactoring in Fragmented Serverless Clusters.

PipeLive: Efficient Live In-place Pipeline Parallelism Reconfiguration for Dynamic LLM Serving FlexPipe: Adapting Dynamic LLM Serving Through Inflight Pipeline Refactoring in Fragmented Serverless Clusters

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-05-12T01:43:48.233906Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation c5439bd0-b6cd-4d53-ba9b-b78903bda18e · outbound

This paper cites Towards swift serverless llm cold starts with paraserve.

PipeLive: Efficient Live In-place Pipeline Parallelism Reconfiguration for Dynamic LLM Serving Towards swift serverless llm cold starts with paraserve

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-11T08:40:59.359869Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation ca6a9112-2b36-4ad9-b71f-122d2479f4fb · outbound

This paper cites an unresolved cited work.

PipeLive: Efficient Live In-place Pipeline Parallelism Reconfiguration for Dynamic LLM Serving Unresolved cited work

Reference 17

Resolution: unresolved; raw_fallback, observed 2026-05-17T14:49:47.155765Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation f3ce4cd1-e77a-41f8-8b16-d2df920e0cfa · outbound

This paper cites InProceedings of the International Conference for High Performance Computing, Networking, Storage, and Analysis (SC).

PipeLive: Efficient Live In-place Pipeline Parallelism Reconfiguration for Dynamic LLM Serving InProceedings of the International Conference for High Performance Computing, Networking, Storage, and Analysis (SC)

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T14:49:47.176860Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 0db0a019-fc17-4c00-bd19-185d66e69e72 · outbound

This paper cites Devanur, Gregory R.

PipeLive: Efficient Live In-place Pipeline Parallelism Reconfiguration for Dynamic LLM Serving Devanur, Gregory R

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T14:49:47.185070Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 93b011cd-6742-417c-b3ec-a77df39ef5e9 · outbound

This paper cites GPT-4 Technical Report.

PipeLive: Efficient Live In-place Pipeline Parallelism Reconfiguration for Dynamic LLM Serving GPT-4 Technical Report

Reference 20

Resolution: verified exact; local_arxiv, observed 2026-05-11T08:40:59.346207Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 3a1a42c5-aace-4cae-a516-b454028ef808 · outbound

This paper cites an unresolved cited work.

PipeLive: Efficient Live In-place Pipeline Parallelism Reconfiguration for Dynamic LLM Serving Unresolved cited work

Reference 21

Resolution: unresolved; raw_fallback, observed 2026-05-17T14:49:47.152148Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation b1d8470f-480a-4857-994b-c2f188c5adc7 · outbound

This paper cites an unresolved cited work.

PipeLive: Efficient Live In-place Pipeline Parallelism Reconfiguration for Dynamic LLM Serving Unresolved cited work

Reference 22

Resolution: unresolved; raw_fallback, observed 2026-05-17T14:49:47.181148Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation d94cfa59-ba15-497a-ad5f-df31906b458a · outbound

This paper cites Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism.

PipeLive: Efficient Live In-place Pipeline Parallelism Reconfiguration for Dynamic LLM Serving Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism

Reference 23

Resolution: verified exact; local_arxiv, observed 2026-05-11T08:40:59.337054Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation e00f810b-d660-46fe-83ec-53617c574060 · outbound

This paper cites an unresolved cited work.

PipeLive: Efficient Live In-place Pipeline Parallelism Reconfiguration for Dynamic LLM Serving Unresolved cited work

Reference 24

Resolution: unresolved; raw_fallback, observed 2026-05-17T14:49:47.126420Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 0f44094b-ec47-4bff-833f-77d3700c79f1 · outbound

This paper cites an unresolved cited work.

PipeLive: Efficient Live In-place Pipeline Parallelism Reconfiguration for Dynamic LLM Serving Unresolved cited work

Reference 25

Resolution: unresolved; raw_fallback, observed 2026-05-17T14:49:47.172359Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 89be5929-f1de-4604-9db0-70ce467ec9b9 · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

PipeLive: Efficient Live In-place Pipeline Parallelism Reconfiguration for Dynamic LLM Serving LLaMA: Open and Efficient Foundation Language Models

Reference 26

Resolution: verified exact; local_arxiv, observed 2026-05-11T08:40:59.330395Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 90de5a4a-a07e-4f9c-bd67-ccc669ec0935 · outbound

This paper cites Gomez, Łukasz Kaiser, and Illia Polosukhin.

PipeLive: Efficient Live In-place Pipeline Parallelism Reconfiguration for Dynamic LLM Serving Gomez, Łukasz Kaiser, and Illia Polosukhin

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T14:49:47.191464Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 4427d524-922e-490d-9c6a-3a068c1fd0df · outbound

This paper cites an unresolved cited work.

PipeLive: Efficient Live In-place Pipeline Parallelism Reconfiguration for Dynamic LLM Serving Unresolved cited work

Reference 28

Resolution: unresolved; raw_fallback, observed 2026-05-17T14:49:47.136086Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation f3962157-bfbe-4d1c-9590-b4b9e999f785 · outbound

This paper cites InProceedings of the ACM SIGOPS 30th Symposium on Operating Systems Principles (SOSP).

PipeLive: Efficient Live In-place Pipeline Parallelism Reconfiguration for Dynamic LLM Serving InProceedings of the ACM SIGOPS 30th Symposium on Operating Systems Principles (SOSP)

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T14:49:47.131786Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation c5cc4f5f-9dad-4df7-949f-8607647b2129 · outbound

This paper cites Towards Efficient and Practical GPU Multitasking in the Era of LLM.

PipeLive: Efficient Live In-place Pipeline Parallelism Reconfiguration for Dynamic LLM Serving Towards Efficient and Practical GPU Multitasking in the Era of LLM

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-05-11T08:40:59.372832Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 05018b1a-ee7e-4c13-8df7-21a9b9c16b63 · outbound

This paper cites an unresolved cited work.

PipeLive: Efficient Live In-place Pipeline Parallelism Reconfiguration for Dynamic LLM Serving Unresolved cited work

Reference 31

Resolution: unresolved; raw_fallback, observed 2026-05-17T14:49:47.169149Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation e040370e-aa81-4450-a6db-8e738d313491 · outbound

This paper cites Qwen3 Technical Report.

PipeLive: Efficient Live In-place Pipeline Parallelism Reconfiguration for Dynamic LLM Serving Qwen3 Technical Report

Reference 32

Resolution: verified exact; local_arxiv, observed 2026-05-11T08:40:59.352592Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 350e2d1e-ae06-41ed-8aa2-0fb5f4c2dac9 · outbound

This paper cites an unresolved cited work.

PipeLive: Efficient Live In-place Pipeline Parallelism Reconfiguration for Dynamic LLM Serving Unresolved cited work

Reference 33

Resolution: unresolved; raw_fallback, observed 2026-05-17T14:49:47.114939Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation b4bcc4ec-f9c9-4876-ba61-f8d763c153a7 · outbound

This paper cites an unresolved cited work.

PipeLive: Efficient Live In-place Pipeline Parallelism Reconfiguration for Dynamic LLM Serving Unresolved cited work

Reference 34

Resolution: unresolved; raw_fallback, observed 2026-05-17T14:49:47.118680Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 5777511c-a141-44ef-9086-12081b85aac0 · outbound

This paper cites Xing, Joseph E.

PipeLive: Efficient Live In-place Pipeline Parallelism Reconfiguration for Dynamic LLM Serving Xing, Joseph E

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T14:49:47.139707Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation c9fbad84-7676-4447-a0a3-bb76c35a7022 · outbound

This paper cites Gonzalez, Clark Barrett, and Ying Sheng.

PipeLive: Efficient Live In-place Pipeline Parallelism Reconfiguration for Dynamic LLM Serving Gonzalez, Clark Barrett, and Ying Sheng

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T14:49:47.143349Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation bfb5e262-e560-428b-8b3c-480d8fd77bae · outbound

This paper cites an unresolved cited work.

PipeLive: Efficient Live In-place Pipeline Parallelism Reconfiguration for Dynamic LLM Serving Unresolved cited work

Reference 37

Resolution: unresolved; raw_fallback, observed 2026-05-17T14:49:47.188302Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Pith citing papers

Observation 2337b840-eaf1-4edf-8271-a11a7d5652c1 · inbound

ReMP: Low-Downtime Runtime Model-Parallelism Reconfiguration for LLM Serving cites this paper.

ReMP: Low-Downtime Runtime Model-Parallelism Reconfiguration for LLM Serving PipeLive: Efficient Live In-place Pipeline Parallelism Reconfiguration for Dynamic LLM Serving

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-07-04T02:39:24.935562Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.