Paper Citation Record · LEDGER

Efficiently Serving Large Multimodal Models Using EPD Disaggregation

As of 19 August 2026, this Paper Citation Record lists 22 of 22 outbound references and 5 inbound Pith citation observations for arXiv:2501.05460.

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

pith.paper-citation-record.v1
2501.05460 v4

Coverage vector

measured 22 of 22 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-11T04:29:34.814139Z

measured 27 of 27 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+00:00

measured 5 of 5 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-14T05:50:05.847560Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-03T10:27:56.708993Z

Reference resolution

22 of 22 outbound references displayed

verified exact0
verified fuzzy8
unresolved14
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation c6a4cebb-9521-4820-ac94-9c94739b3328 · outbound

This paper cites write newline.

Efficiently Serving Large Multimodal Models Using EPD Disaggregation write newline

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-11T04:29:34.674265Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81c278c7-4849-44d0-9d21-2051357c10b3 · outbound

This paper cites GPT-4 Technical Report.

Efficiently Serving Large Multimodal Models Using EPD Disaggregation GPT-4 Technical Report

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-11T04:29:34.682023Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 159e985a-df5e-4fb8-895a-24eba915a341 · outbound

This paper cites SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills.

Efficiently Serving Large Multimodal Models Using EPD Disaggregation SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-11T04:29:34.688512Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d368e730-0f3a-4b4b-bf29-ddbf99e9d34c · outbound

This paper cites Bayesian performance analysis for black-box optimization benchmarking.

Efficiently Serving Large Multimodal Models Using EPD Disaggregation Bayesian performance analysis for black-box optimization benchmarking

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T04:29:35.332131Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 7115aa6f-977d-4886-a4fa-bf59f60a44de · outbound

This paper cites A survey on evaluation of large language models.

Efficiently Serving Large Multimodal Models Using EPD Disaggregation A survey on evaluation of large language models

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-11T04:29:34.702705Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b5c4a0e-3eb6-4663-9f5d-4bcc72741d2a · outbound

This paper cites an unresolved cited work.

Efficiently Serving Large Multimodal Models Using EPD Disaggregation Unresolved cited work

Reference 6

Resolution: unresolved; raw_fallback, observed 2026-08-11T04:29:35.290259Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 4bfc5aba-9f8e-4f16-807a-02fa3f311093 · outbound

This paper cites Inference without Interference: Disaggregate LLM Inference for Mixed Downstream Workloads.

Efficiently Serving Large Multimodal Models Using EPD Disaggregation Inference without Interference: Disaggregate LLM Inference for Mixed Downstream Workloads

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-11T04:29:34.715304Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0117dca-f92c-49d7-9e15-5433c53e1873 · outbound

This paper cites P/D-Serve: Serving Disaggregated Large Language Model at Scale.

Efficiently Serving Large Multimodal Models Using EPD Disaggregation P/D-Serve: Serving Disaggregated Large Language Model at Scale

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-11T04:29:34.722701Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2377e117-9098-4867-96d4-78956e29de2a · outbound

This paper cites GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM.

Efficiently Serving Large Multimodal Models Using EPD Disaggregation GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-11T04:29:34.728199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 15dd31be-cc95-4cb3-ba54-d9daf26363bd · outbound

This paper cites Gonzalez, Hao Zhang, and Ion Stoica.

Efficiently Serving Large Multimodal Models Using EPD Disaggregation Gonzalez, Hao Zhang, and Ion Stoica

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-11T04:29:34.734734Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97a7ee87-fa7b-44fd-a5b2-3782d8931485 · outbound

This paper cites SnapKV: LLM Knows What You are Looking for Before Generation.

Efficiently Serving Large Multimodal Models Using EPD Disaggregation SnapKV: LLM Knows What You are Looking for Before Generation

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-11T04:29:34.741541Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73c28bde-86c0-41e9-9b92-df4fa936a110 · outbound

This paper cites Visual instruction tuning.

Efficiently Serving Large Multimodal Models Using EPD Disaggregation Visual instruction tuning

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T04:29:35.255190Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 6228cef4-4dd2-4c59-a563-b9bd40c58774 · outbound

This paper cites A Survey of Resource-efficient LLM and Multimodal Foundation Models.

Efficiently Serving Large Multimodal Models Using EPD Disaggregation A Survey of Resource-efficient LLM and Multimodal Foundation Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-11T04:29:34.754050Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dff5c09c-b35e-4453-a966-7649deab5b34 · outbound

This paper cites Inf-MLLM: Efficient Streaming Inference of Multimodal Large Language Models on a Single GPU.

Efficiently Serving Large Multimodal Models Using EPD Disaggregation Inf-MLLM: Efficient Streaming Inference of Multimodal Large Language Models on a Single GPU

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-11T04:29:34.761337Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e71c408-6d18-48c6-b9ce-04c7d489c5c6 · outbound

This paper cites Splitwise: Efficient generative llm inference using phase splitting.

Efficiently Serving Large Multimodal Models Using EPD Disaggregation Splitwise: Efficient generative llm inference using phase splitting

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T04:29:35.230980Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 40f4ea5e-993e-4f6c-a998-6dfd33b497e4 · outbound

This paper cites Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving.

Efficiently Serving Large Multimodal Models Using EPD Disaggregation Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-11T04:29:34.773621Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94c49337-4b17-45cb-943c-27d8b7d00f4a · outbound

This paper cites Déjàvu: Kv-cache streaming for fast, fault-tolerant generative llm serving.

Efficiently Serving Large Multimodal Models Using EPD Disaggregation Déjàvu: Kv-cache streaming for fast, fault-tolerant generative llm serving

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T04:29:35.210047Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 338d2da4-22cc-4777-afe7-9b661fd0bbc2 · outbound

This paper cites Multimodal large language models: A survey.

Efficiently Serving Large Multimodal Models Using EPD Disaggregation Multimodal large language models: A survey

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T04:29:35.190521Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation fd044171-a942-48a2-b84e-255b46599e40 · outbound

This paper cites Next-qa: Next phase of question-answering to explaining temporal actions.

Efficiently Serving Large Multimodal Models Using EPD Disaggregation Next-qa: Next phase of question-answering to explaining temporal actions

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T04:29:35.167832Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 5e4a0f9a-7f97-42a2-893c-ebb612184070 · outbound

This paper cites MiniCPM-V: A GPT-4V Level MLLM on Your Phone.

Efficiently Serving Large Multimodal Models Using EPD Disaggregation MiniCPM-V: A GPT-4V Level MLLM on Your Phone

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-11T04:29:34.801288Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67b3ed10-eb80-449a-9dbf-e10719527c3a · outbound

This paper cites Orca: A distributed serving system for Transformer-Based generative models.

Efficiently Serving Large Multimodal Models Using EPD Disaggregation Orca: A distributed serving system for Transformer-Based generative models

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T04:29:35.144618Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 22e01768-2e30-4e87-ac5c-33606952ea2c · outbound

This paper cites Distserve: Disaggregating prefill and decoding for goodput-optimized large language model serving.

Efficiently Serving Large Multimodal Models Using EPD Disaggregation Distserve: Disaggregating prefill and decoding for goodput-optimized large language model serving

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T04:29:35.124767Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Pith citing papers

Observation b31d7bd5-83c8-41cd-9bf8-4f1d994fd4cf · inbound

Taming Request Imbalance: SLO-Aware Scheduling for Disaggregated LLM Inference cites this paper.

Taming Request Imbalance: SLO-Aware Scheduling for Disaggregated LLM Inference Efficiently Serving Large Multimodal Models Using EPD Disaggregation

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-09T06:25:46.433228Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation fbf9efa4-beef-43dd-a7d5-9b06a76d13ae · inbound

Taming Request Imbalance: SLO-Aware Scheduling for Disaggregated LLM Inference cites this paper.

Taming Request Imbalance: SLO-Aware Scheduling for Disaggregated LLM Inference Efficiently Serving Large Multimodal Models Using EPD Disaggregation

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-07-01T00:35:10.220523Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 8f6663c9-ffdd-45ef-81fa-24d7aa46c2c0 · inbound

RTP-LLM: High-Performance Alibaba LLM Inference Engine cites this paper.

RTP-LLM: High-Performance Alibaba LLM Inference Engine Efficiently Serving Large Multimodal Models Using EPD Disaggregation

Reference 46

Resolution: metadata mismatch; arxiv_id, observed 2026-06-28T23:52:49.116085Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 6dfd23c0-4950-4a8d-8547-2c2653179600 · inbound

M*: A Modular, Extensible, Serving System for Multimodal Models cites this paper.

M*: A Modular, Extensible, Serving System for Multimodal Models Efficiently Serving Large Multimodal Models Using EPD Disaggregation

Reference 34

Resolution: verified exact; arxiv_id, observed 2026-07-03T10:27:56.710430Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation c9ad68a2-064b-453d-9a35-568e673923f5 · inbound

OpScale: Operator-level Provisioning and Autoscaling for LLM Serving cites this paper.

OpScale: Operator-level Provisioning and Autoscaling for LLM Serving Efficiently Serving Large Multimodal Models Using EPD Disaggregation

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-14T05:50:05.847560Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.