Paper Citation Record · LEDGER

Energy-Efficient Multimodal Inference Serving with Tri-serve

As of 20 August 2026, this Paper Citation Record lists 34 of 34 outbound references and 0 inbound Pith citation observations for arXiv:2606.29629.

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

pith.paper-citation-record.v1
2606.29629 v2

Coverage vector

measured 34 of 34 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-01T06:27:38.667047Z

measured 34 of 34 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-20T06:33:59.587034+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

34 of 34 outbound references displayed

verified exact8
verified fuzzy26
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation d5c286a1-0c6a-4613-b99a-59545af3f91f · outbound

This paper cites Claude code: Agentic coding in the terminal,.

Energy-Efficient Multimodal Inference Serving with Tri-serve Claude code: Agentic coding in the terminal,

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T18:12:47.420082Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation a3ba370b-ef3b-42d2-92cf-5cb9616053b5 · outbound

This paper cites Cursor: The AI code editor,.

Energy-Efficient Multimodal Inference Serving with Tri-serve Cursor: The AI code editor,

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T18:12:47.407970Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 19d0e6fd-5a8a-43c5-917b-a8a637a46f0e · outbound

This paper cites Openai codex: A cloud-based software engineering agent,.

Energy-Efficient Multimodal Inference Serving with Tri-serve Openai codex: A cloud-based software engineering agent,

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T18:12:47.404548Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation b6fd3380-0281-41af-9a8c-93299d758395 · outbound

This paper cites OpenClaw: An open-source conversational AI assistant,.

Energy-Efficient Multimodal Inference Serving with Tri-serve OpenClaw: An open-source conversational AI assistant,

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T18:12:47.415541Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation e528c900-77a9-4a39-baaf-2579548c32d1 · outbound

This paper cites Introducing ChatGPT,.

Energy-Efficient Multimodal Inference Serving with Tri-serve Introducing ChatGPT,

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T18:12:47.417857Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation d7155c01-e741-4b23-bd2d-8b6d1b9c0879 · outbound

This paper cites Gemini: A family of highly capable multimodal models,.

Energy-Efficient Multimodal Inference Serving with Tri-serve Gemini: A family of highly capable multimodal models,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T18:12:47.421089Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation a9f89783-0c96-4968-96b5-22184cd7aac2 · outbound

This paper cites vllm-omni: Fully disaggregated serving for any-to-any multimodal models.

Energy-Efficient Multimodal Inference Serving with Tri-serve vllm-omni: Fully disaggregated serving for any-to-any multimodal models

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-07-01T09:35:40.148389Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation e2e64eb2-4955-4928-8523-e39dddaf2ce4 · outbound

This paper cites Char- acterizing power management opportunities for llms in the cloud,.

Energy-Efficient Multimodal Inference Serving with Tri-serve Char- acterizing power management opportunities for llms in the cloud,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T18:12:47.425456Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation a7f6313d-d51c-4c7b-abd5-ef3634ccf550 · outbound

This paper cites Slo-aware gpu dvfs for energy-efficient llm inference serving,.

Energy-Efficient Multimodal Inference Serving with Tri-serve Slo-aware gpu dvfs for energy-efficient llm inference serving,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T18:12:47.413395Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 527ba693-683e-428c-8719-5b88f56fe85e · outbound

This paper cites Power-aware deep learning model serving withµ-Serve,.

Energy-Efficient Multimodal Inference Serving with Tri-serve Power-aware deep learning model serving withµ-Serve,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T18:12:47.399117Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation d69606d9-18b5-46d3-a0e6-fee700a0794e · outbound

This paper cites throttll’em: Predictive gpu throttling for energy efficient llm inference serving,.

Energy-Efficient Multimodal Inference Serving with Tri-serve throttll’em: Predictive gpu throttling for energy efficient llm inference serving,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T18:12:47.431811Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 17e0293e-dc60-47ec-a524-c2ce7c6d554f · outbound

This paper cites Qwen2.5-Coder Technical Report.

Energy-Efficient Multimodal Inference Serving with Tri-serve Qwen2.5-Coder Technical Report

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-07-01T09:35:40.135922Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 132dc57d-3755-4936-b325-06152beab585 · outbound

This paper cites Qwen3 Technical Report.

Energy-Efficient Multimodal Inference Serving with Tri-serve Qwen3 Technical Report

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-07-01T09:35:40.138454Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 282c593d-5717-4e79-9e3c-753abfc38793 · outbound

This paper cites Qwen3-Omni Technical Report.

Energy-Efficient Multimodal Inference Serving with Tri-serve Qwen3-Omni Technical Report

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-07-01T09:35:40.143346Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 10f572e2-c417-4e51-8928-28db42f9be6f · outbound

This paper cites An integrated gpu power and performance model,.

Energy-Efficient Multimodal Inference Serving with Tri-serve An integrated gpu power and performance model,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T18:12:47.430432Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation fed2222c-2ed4-4ce3-98c6-69cdcc62adb7 · outbound

This paper cites Gpgpu power modeling for multi-domain voltage-frequency scaling.

Energy-Efficient Multimodal Inference Serving with Tri-serve Gpgpu power modeling for multi-domain voltage-frequency scaling

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T18:12:47.393480Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation ddd73b4d-9be0-4624-a79d-295116d08990 · outbound

This paper cites Leakage temperature dependency mod- eling in system level analysis,.

Energy-Efficient Multimodal Inference Serving with Tri-serve Leakage temperature dependency mod- eling in system level analysis,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T18:12:47.394576Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 942cc37e-82bd-438c-9346-c776b4bd9cff · outbound

This paper cites Qwen3.5-Omni Technical Report.

Energy-Efficient Multimodal Inference Serving with Tri-serve Qwen3.5-Omni Technical Report

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-07-01T09:35:40.145125Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 72605d58-30e0-4176-971a-32a348509dde · outbound

This paper cites MME-Unify: A Comprehensive Benchmark for Unified Multimodal Understanding and Generation Models.

Energy-Efficient Multimodal Inference Serving with Tri-serve MME-Unify: A Comprehensive Benchmark for Unified Multimodal Understanding and Generation Models

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-07-01T09:35:40.139825Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 823a54b9-05d4-4431-b8b3-71d218f2c44a · outbound

This paper cites Efficient memory management for large language model serving with pagedattention,.

Energy-Efficient Multimodal Inference Serving with Tri-serve Efficient memory management for large language model serving with pagedattention,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T18:12:47.396965Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation c131f6e1-6442-453a-abf6-b26ab7b42d6a · outbound

This paper cites The Energy Cost of Execution-Idle in GPU Clusters.

Energy-Efficient Multimodal Inference Serving with Tri-serve The Energy Cost of Execution-Idle in GPU Clusters

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-07-01T09:35:40.146701Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation c1187d13-b936-479d-9578-f5c89bb263b7 · outbound

This paper cites Pccl: Energy-efficient llm training with power-aware collective communication,.

Energy-Efficient Multimodal Inference Serving with Tri-serve Pccl: Energy-efficient llm training with power-aware collective communication,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T18:12:47.401531Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation f3c85e6a-ef0c-4d3c-8673-8a1e0fdb41e0 · outbound

This paper cites Towards improved power management in cloud gpus,.

Energy-Efficient Multimodal Inference Serving with Tri-serve Towards improved power management in cloud gpus,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T18:12:47.427369Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation bef77a55-4e9f-46aa-90ad-f0e3d525e7da · outbound

This paper cites Roofline: an insightful visual performance model for multicore architectures,.

Energy-Efficient Multimodal Inference Serving with Tri-serve Roofline: an insightful visual performance model for multicore architectures,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T18:12:47.411093Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 4bbafe44-fd88-45c0-ab82-51c69ead4719 · outbound

This paper cites Nvidia nsight compute: Gpu profiler,.

Energy-Efficient Multimodal Inference Serving with Tri-serve Nvidia nsight compute: Gpu profiler,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T18:12:47.391400Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation b0f7c85a-8e85-4a76-a55f-9b5360a27182 · outbound

This paper cites Seed-TTS: A Family of High-Quality Versatile Speech Generation Models.

Energy-Efficient Multimodal Inference Serving with Tri-serve Seed-TTS: A Family of High-Quality Versatile Speech Generation Models

Reference 26

Resolution: verified exact; local_arxiv, observed 2026-07-01T09:35:40.128634Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation e7d62c1b-dc25-44b6-8159-ec8743c30e92 · outbound

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

Energy-Efficient Multimodal Inference Serving with Tri-serve Orca: A distributed serving system for Transformer-Based generative models,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T18:12:47.383383Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 0d5c8e11-07a3-4d0f-a58b-a29159ba9b4f · outbound

This paper cites Taming Throughput-Latency tradeoff in LLM inference with Sarathi-Serve,.

Energy-Efficient Multimodal Inference Serving with Tri-serve Taming Throughput-Latency tradeoff in LLM inference with Sarathi-Serve,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T18:12:47.385634Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 7ac8c1a4-c5a7-422f-bd9d-3398fb178e3a · outbound

This paper cites AlpaServe: Statistical multiplexing with model parallelism for deep learning serving,.

Energy-Efficient Multimodal Inference Serving with Tri-serve AlpaServe: Statistical multiplexing with model parallelism for deep learning serving,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T18:12:47.423405Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation a64ee6e5-fe42-4c60-8525-814e1efa8043 · outbound

This paper cites DistServe: Disaggre- gating prefill and decoding for goodput-optimized large language model serving,.

Energy-Efficient Multimodal Inference Serving with Tri-serve DistServe: Disaggre- gating prefill and decoding for goodput-optimized large language model serving,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T18:12:47.381563Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 282c43f5-3846-4846-8bdd-722fbc28c939 · outbound

This paper cites Powerinfer: Fast large language model serving with a consumer-grade gpu,.

Energy-Efficient Multimodal Inference Serving with Tri-serve Powerinfer: Fast large language model serving with a consumer-grade gpu,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T18:12:47.387687Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 5d03c734-4df6-40ee-9c48-fac1379964d8 · outbound

This paper cites Towards sustainable ai: a comprehensive framework for green ai,.

Energy-Efficient Multimodal Inference Serving with Tri-serve Towards sustainable ai: a comprehensive framework for green ai,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T18:12:47.389413Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 3e208255-8281-455d-8778-b9bb3afd5a23 · outbound

This paper cites Hotspot: a compact thermal modeling methodology for early- stage vlsi design,.

Energy-Efficient Multimodal Inference Serving with Tri-serve Hotspot: a compact thermal modeling methodology for early- stage vlsi design,

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T18:12:47.379533Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 61826b4f-3050-433b-bd5f-3ffa1ad5ee90 · outbound

This paper cites Roofline-aware dvfs for gpus,.

Energy-Efficient Multimodal Inference Serving with Tri-serve Roofline-aware dvfs for gpus,

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T18:12:47.377432Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Pith citing papers

No inbound Pith citation observations are available.