Paper Citation Record · LEDGER

EcoServe: Designing Carbon-Aware AI Inference Systems

As of 19 August 2026, this Paper Citation Record lists 90 of 90 outbound references and 15 inbound Pith citation observations for arXiv:2502.05043.

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

pith.paper-citation-record.v1
2502.05043 v2

Coverage vector

measured 90 of 90 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-08T20:31:35.870375Z

measured 105 of 105 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+00:00

measured 15 of 15 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T16:30:34.981682Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-04T02:29:23.910827Z

Reference resolution

90 of 90 outbound references displayed

verified exact0
verified fuzzy51
unresolved38
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation b9fc4737-f092-4758-ae2b-a62df3c92291 · outbound

This paper cites https:// lambdalabs.com/service/gpu-cloud.

EcoServe: Designing Carbon-Aware AI Inference Systems https:// lambdalabs.com/service/gpu-cloud

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-08T20:31:35.568020Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c2888aa-75a9-44ab-ab57-fc99bfda0c0c · outbound

This paper cites an unresolved cited work.

EcoServe: Designing Carbon-Aware AI Inference Systems Unresolved cited work

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-08T20:31:35.572073Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f39646b-6e08-497a-9a1c-e20635c7a3ed · outbound

This paper cites https://news.skhynix.com/hbm2e- opens-the-era-of-ultra-speed-memory-semiconductors/.

EcoServe: Designing Carbon-Aware AI Inference Systems https://news.skhynix.com/hbm2e- opens-the-era-of-ultra-speed-memory-semiconductors/

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-08T20:31:35.575843Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3657a43a-1562-4dda-8912-7eea37efdd80 · outbound

This paper cites [Available Online] https://developer.nvidia.com/tensorrt/, 2023.

EcoServe: Designing Carbon-Aware AI Inference Systems [Available Online] https://developer.nvidia.com/tensorrt/, 2023

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-08T20:31:35.579381Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5dc2b9d4-5324-4475-8bc8-f7f508d5946f · outbound

This paper cites Carbon explorer: A holis- tic framework for designing carbon aware datacenters.

EcoServe: Designing Carbon-Aware AI Inference Systems Carbon explorer: A holis- tic framework for designing carbon aware datacenters

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-08T20:31:35.582814Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7f4eaf5-f73f-49ec-bc5c-55264a0a7e01 · outbound

This paper cites Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve.

EcoServe: Designing Carbon-Aware AI Inference Systems Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-08T20:31:35.586278Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3af02b93-21e5-451e-8782-277fa6ee575c · outbound

This paper cites Deepspeed- inference: Enabling efficient inference of trans- former models at unprecedented scale.

EcoServe: Designing Carbon-Aware AI Inference Systems Deepspeed- inference: Enabling efficient inference of trans- former models at unprecedented scale

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-08T20:31:35.590178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 305c4472-2da1-4e35-872b-f99e6b85bcee · outbound

This paper cites Aws recommended gpu instances, 2024.

EcoServe: Designing Carbon-Aware AI Inference Systems Aws recommended gpu instances, 2024

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-08T20:31:35.593951Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2227d5ea-65a4-47a1-b9c8-d1ead4542a3e · outbound

This paper cites Azure gpu optimized virtual machine sizes, 2024.

EcoServe: Designing Carbon-Aware AI Inference Systems Azure gpu optimized virtual machine sizes, 2024

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-08T20:31:35.597303Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5cc6b4d6-a16e-430e-9f7c-9bc52a81b52d · outbound

This paper cites Life cycle assessment – dell r740.

EcoServe: Designing Carbon-Aware AI Inference Systems Life cycle assessment – dell r740

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-08T20:31:35.600698Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7edb045d-78cb-4fdb-be57-7449823055a1 · outbound

This paper cites Flashdecoding: Accelerating llm inference by paralleling token generation.

EcoServe: Designing Carbon-Aware AI Inference Systems Flashdecoding: Accelerating llm inference by paralleling token generation

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-08T20:31:35.604161Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95fc0834-bbe9-4e35-8928-bfd93035251e · outbound

This paper cites Palm: Scaling language modeling with pathways.

EcoServe: Designing Carbon-Aware AI Inference Systems Palm: Scaling language modeling with pathways

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:31:36.881262Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation a2bd32e2-e792-4e93-9b7f-dbc305d67b33 · outbound

This paper cites Sharegpt: A dataset of multi-turn chat interactions with large language models.

EcoServe: Designing Carbon-Aware AI Inference Systems Sharegpt: A dataset of multi-turn chat interactions with large language models

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:31:36.870842Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 39171c62-d14f-4745-bd0e-139e45d950ee · outbound

This paper cites Clipper: A{Low-Latency} online prediction serving system.

EcoServe: Designing Carbon-Aware AI Inference Systems Clipper: A{Low-Latency} online prediction serving system

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:31:36.860115Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation e8dbdfb1-cae4-4f6e-a2cb-3ec77a0e593a · outbound

This paper cites FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning.

EcoServe: Designing Carbon-Aware AI Inference Systems FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-08T20:31:35.617893Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9adbddd2-4015-40b7-a789-66f92dcb3d06 · outbound

This paper cites Flashattention: Fast and memory-efficient exact attention with io-awareness.

EcoServe: Designing Carbon-Aware AI Inference Systems Flashattention: Fast and memory-efficient exact attention with io-awareness

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-08T20:31:35.621631Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a46a3bee-fd2c-4805-a4d0-e7df5eb46da6 · outbound

This paper cites Hanebutte, Rahul Khanna, and Chris- tian Le.

EcoServe: Designing Carbon-Aware AI Inference Systems Hanebutte, Rahul Khanna, and Chris- tian Le

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:31:36.843727Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 3e3f3c86-b515-456e-980c-dd31240fe1e2 · outbound

This paper cites Openblas: An optimized blas library.

EcoServe: Designing Carbon-Aware AI Inference Systems Openblas: An optimized blas library

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:31:36.833547Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 2b573dc4-c098-41e3-9e25-c72e20fc0613 · outbound

This paper cites Cvxpy: A python-embedded modeling language for convex optimization, 2024.

EcoServe: Designing Carbon-Aware AI Inference Systems Cvxpy: A python-embedded modeling language for convex optimization, 2024

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:31:36.823825Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation ab2e0b0b-f223-402b-8100-13aa032e80fe · outbound

This paper cites SiDA-MoE: Sparsity-Inspired Data-Aware Serving for Efficient and Scalable Large Mixture-of-Experts Models.

EcoServe: Designing Carbon-Aware AI Inference Systems SiDA-MoE: Sparsity-Inspired Data-Aware Serving for Efficient and Scalable Large Mixture-of-Experts Models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-08T20:31:35.635288Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce0702e5-ca18-46b9-9953-46291e4cb772 · outbound

This paper cites Focal: A first-order carbon model to assess processor sustain- ability.

EcoServe: Designing Carbon-Aware AI Inference Systems Focal: A first-order carbon model to assess processor sustain- ability

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:31:36.813890Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation e6544a4e-09c1-42c3-9cda-bafa56a25dae · outbound

This paper cites 72-hour hourly map.

EcoServe: Designing Carbon-Aware AI Inference Systems 72-hour hourly map

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:31:36.802522Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation f2242299-863c-4b8f-b325-9094d10aaffa · outbound

This paper cites LLMCarbon: Modeling the end-to-end Carbon Footprint of Large Language Models.

EcoServe: Designing Carbon-Aware AI Inference Systems LLMCarbon: Modeling the end-to-end Carbon Footprint of Large Language Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-08T20:31:35.646240Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation adb58592-0801-43ad-b21b-0ea8cd9737ce · outbound

This paper cites Mobius: Fine tuning large-scale models on commodity gpu servers.

EcoServe: Designing Carbon-Aware AI Inference Systems Mobius: Fine tuning large-scale models on commodity gpu servers

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:31:36.792093Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 73aa6d10-915c-42ec-a706-a0033c33c2f0 · outbound

This paper cites Garcia Bardon, P.

EcoServe: Designing Carbon-Aware AI Inference Systems Garcia Bardon, P

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:31:36.781246Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 067bb4a1-6eae-4193-a57f-111198d45674 · outbound

This paper cites Llama.cpp: Inference of llama models in pure c/c++.

EcoServe: Designing Carbon-Aware AI Inference Systems Llama.cpp: Inference of llama models in pure c/c++

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:31:36.771087Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation cd79462a-24d6-49cd-a076-e2151a0b4ca9 · outbound

This paper cites Gemma.cpp: Efficient inference for large language models.

EcoServe: Designing Carbon-Aware AI Inference Systems Gemma.cpp: Efficient inference for large language models

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:31:36.760539Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation fde478b0-776f-4412-a3d8-f1815186f09e · outbound

This paper cites Google sustainability report, 2024.

EcoServe: Designing Carbon-Aware AI Inference Systems Google sustainability report, 2024

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:31:36.750135Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 5f6b608b-05ca-4a69-9909-3c2256aa59ec · outbound

This paper cites Mélange: Cost efficient large language model serving by exploiting gpu heterogeneity, 2024.

EcoServe: Designing Carbon-Aware AI Inference Systems Mélange: Cost efficient large language model serving by exploiting gpu heterogeneity, 2024

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:31:36.739587Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 00f4c459-a11b-4644-9d74-10e6b42f9d7f · outbound

This paper cites Serving{DNNs} like clockwork: Performance predictability from the bottom up.

EcoServe: Designing Carbon-Aware AI Inference Systems Serving{DNNs} like clockwork: Performance predictability from the bottom up

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:31:36.729259Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation f8f17fb8-5cdf-40c6-b16e-7c8f868b1976 · outbound

This paper cites Lee, David Brooks, and Carole-Jean Wu.

EcoServe: Designing Carbon-Aware AI Inference Systems Lee, David Brooks, and Carole-Jean Wu

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:31:36.718440Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 36b74b4d-7542-4ff4-952c-cc0ff41b5fc2 · outbound

This paper cites Chasing carbon: The elusive environmental footprint of computing.

EcoServe: Designing Carbon-Aware AI Inference Systems Chasing carbon: The elusive environmental footprint of computing

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:31:36.707146Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 610edb82-c357-4d9a-9513-9c86109dd002 · outbound

This paper cites FastDecode: High-Throughput GPU-Efficient LLM Serving using Heterogeneous Pipelines.

EcoServe: Designing Carbon-Aware AI Inference Systems FastDecode: High-Throughput GPU-Efficient LLM Serving using Heterogeneous Pipelines

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-08T20:31:35.676302Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 751b4ea8-832f-4923-9adf-d3417765cea8 · outbound

This paper cites FlashDecoding++: Faster Large Language Model Inference on GPUs.

EcoServe: Designing Carbon-Aware AI Inference Systems FlashDecoding++: Faster Large Language Model Inference on GPUs

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-08T20:31:35.679828Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0025a02f-5df8-4de8-9066-4e569bdd6a9d · outbound

This paper cites Towards MoE Deployment: Mitigating Inefficiencies in Mixture-of-Expert (MoE) Inference.

EcoServe: Designing Carbon-Aware AI Inference Systems Towards MoE Deployment: Mitigating Inefficiencies in Mixture-of-Expert (MoE) Inference

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-08T20:31:35.683723Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fbe5a570-dd2a-448a-b83b-1ae4e935f5ec · outbound

This paper cites Advancing Environmental Sustainability in Data Centers via Carbon Depreciation Models.

EcoServe: Designing Carbon-Aware AI Inference Systems Advancing Environmental Sustainability in Data Centers via Carbon Depreciation Models

Reference 36

Resolution: metadata mismatch; local_arxiv, observed 2026-08-08T20:31:36.225397Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b9597ea9-18a4-4ec5-b006-86d5a145ddc2 · outbound

This paper cites Neo: Saving gpu memory crisis with cpu offloading for online llm inference, 2024.

EcoServe: Designing Carbon-Aware AI Inference Systems Neo: Saving gpu memory crisis with cpu offloading for online llm inference, 2024

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:31:36.696254Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 5776d0c1-1295-4286-a96e-2d956b559ecb · outbound

This paper cites an unresolved cited work.

EcoServe: Designing Carbon-Aware AI Inference Systems Unresolved cited work

Reference 38

Resolution: unresolved; raw_fallback, observed 2026-08-08T20:31:36.686179Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 6eda6d94-b0bf-4a8d-87fd-0bc9d75d1e12 · outbound

This paper cites Profiling a warehouse-scale computer.

EcoServe: Designing Carbon-Aware AI Inference Systems Profiling a warehouse-scale computer

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:31:36.676275Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 40e33f3d-bfc6-475e-9e54-5f7fcd879ed8 · outbound

This paper cites Backblaze hard drive stats for q2 2021, 2021.

EcoServe: Designing Carbon-Aware AI Inference Systems Backblaze hard drive stats for q2 2021, 2021

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:31:36.665706Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 019e539f-2c11-4e2e-9ee7-ebebf948bffa · outbound

This paper cites SwapMoE: Serving Off-the-shelf MoE-based Large Language Models with Tunable Memory Budget.

EcoServe: Designing Carbon-Aware AI Inference Systems SwapMoE: Serving Off-the-shelf MoE-based Large Language Models with Tunable Memory Budget

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-08T20:31:35.704164Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 295bcb9b-a876-4604-a33f-6bf74895da59 · outbound

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

EcoServe: Designing Carbon-Aware AI Inference Systems Gonzalez, Hao Zhang, and Ion Stoica

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-08T20:31:35.707748Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 468dabca-80cc-4328-b0bf-230cd1c1809a · outbound

This paper cites Amp: Automatically finding model parallel strategies with heterogeneity awareness.

EcoServe: Designing Carbon-Aware AI Inference Systems Amp: Automatically finding model parallel strategies with heterogeneity awareness

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:31:36.649233Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation a92e2b86-aa29-4a67-8967-2a0a95295477 · outbound

This paper cites In 17th USENIX Symposium on Operating Systems Design and Implementation (OSDI 23) , pages 663–679, 2023.

EcoServe: Designing Carbon-Aware AI Inference Systems In 17th USENIX Symposium on Operating Systems Design and Implementation (OSDI 23) , pages 663–679, 2023

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:31:36.639086Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 8628e28a-10eb-4f35-80b7-dd3367e0d92a · outbound

This paper cites Gonzalez, and Ion Stoica.

EcoServe: Designing Carbon-Aware AI Inference Systems Gonzalez, and Ion Stoica

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:31:36.628983Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 240064bb-ea63-46c5-8375-1b6fd1c28a61 · outbound

This paper cites New insight into the aging induced retention time degraded of advanced dram technology.

EcoServe: Designing Carbon-Aware AI Inference Systems New insight into the aging induced retention time degraded of advanced dram technology

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:31:36.618564Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 07360025-7e79-45e6-b153-e9bbcfe121c3 · outbound

This paper cites Cachegen: Kv cache compression and streaming for fast large language model serving.

EcoServe: Designing Carbon-Aware AI Inference Systems Cachegen: Kv cache compression and streaming for fast large language model serving

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:31:36.608388Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 9e9ab4bf-a637-421e-990e-bdd2d023e5a3 · outbound

This paper cites Longbench: A bilingual long-context benchmark for large language models.

EcoServe: Designing Carbon-Aware AI Inference Systems Longbench: A bilingual long-context benchmark for large language models

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:31:36.598434Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation e344bcf9-7758-42e3-90f1-0144a1f91a3f · outbound

This paper cites Deja vu: Contextual sparsity for efficient LLMs at inference time.

EcoServe: Designing Carbon-Aware AI Inference Systems Deja vu: Contextual sparsity for efficient LLMs at inference time

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:31:36.588828Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 1eef6046-f17d-4944-96b7-23e7c6643792 · outbound

This paper cites Power hungry processing: Watts driving the cost of ai deployment? In The 2024 ACM Conference on Fairness, Accountability, and Transparency, pages 85–99, 2024.

EcoServe: Designing Carbon-Aware AI Inference Systems Power hungry processing: Watts driving the cost of ai deployment? In The 2024 ACM Conference on Fairness, Accountability, and Transparency, pages 85–99, 2024

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:31:36.579223Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation e90f9fba-9644-48d7-95b4-e75fe7430ea5 · outbound

This paper cites Helix: Serving Large Language Models over Heterogeneous GPUs and Network via Max-Flow.

EcoServe: Designing Carbon-Aware AI Inference Systems Helix: Serving Large Language Models over Heterogeneous GPUs and Network via Max-Flow

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-08T20:31:35.738204Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 86ed8b63-980f-4fcd-8758-39f0b6f20705 · outbound

This paper cites A large-scale study of flash memory failures in the field.

EcoServe: Designing Carbon-Aware AI Inference Systems A large-scale study of flash memory failures in the field

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:31:36.568895Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 2c5958a6-6bfd-415b-b8a3-32a6ef6603f0 · outbound

This paper cites Microsoft sustainability report, 2024.

EcoServe: Designing Carbon-Aware AI Inference Systems Microsoft sustainability report, 2024

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:31:36.558568Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 2e173302-8bdf-483c-aeeb-ed9988967a96 · outbound

This paper cites Azure public dataset.

EcoServe: Designing Carbon-Aware AI Inference Systems Azure public dataset

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:31:36.548906Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 326b835c-122a-4966-9fe3-68fe2b7a08a0 · outbound

This paper cites Roofline Performance Model - NERSC Documentation — docs.nersc.gov.

EcoServe: Designing Carbon-Aware AI Inference Systems Roofline Performance Model - NERSC Documentation — docs.nersc.gov

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:31:36.538998Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 766bd0cc-675a-44ba-8f72-9d96cc0dfba9 · outbound

This paper cites Nvml api reference, 2024.

EcoServe: Designing Carbon-Aware AI Inference Systems Nvml api reference, 2024

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:31:36.529052Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 83cf973d-a198-4d38-98e2-1542321fb3be · outbound

This paper cites Deep learning performance guide: Matrix multiplication (gemm).

EcoServe: Designing Carbon-Aware AI Inference Systems Deep learning performance guide: Matrix multiplication (gemm)

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:31:36.518833Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 8b74c7f6-5b99-4fbf-8864-1449e822c105 · outbound

This paper cites onednn: Deep neural network library.

EcoServe: Designing Carbon-Aware AI Inference Systems onednn: Deep neural network library

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:31:36.508252Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 940d4e1a-e674-4ce5-98c6-13fe7583d90b · outbound

This paper cites InstInfer: In-Storage Attention Offloading for Cost-Effective Long-Context LLM Inference.

EcoServe: Designing Carbon-Aware AI Inference Systems InstInfer: In-Storage Attention Offloading for Cost-Effective Long-Context LLM Inference

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-08T20:31:35.764869Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31dba348-38de-492c-90d9-29648527d876 · outbound

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

EcoServe: Designing Carbon-Aware AI Inference Systems Splitwise: Efficient generative LLM inference using phase splitting

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-08T20:31:35.768398Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ab383a2-8481-4eed-8da1-07fc6111e0be · outbound

This paper cites an unresolved cited work.

EcoServe: Designing Carbon-Aware AI Inference Systems Unresolved cited work

Reference 61

Resolution: unresolved; raw_fallback, observed 2026-08-08T20:31:36.498296Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 89ba1b1c-7f17-4e2c-a4ef-7fc51a53acba · outbound

This paper cites Deepspeed: System optimizations enable training deep learning models with over 100 billion parameters.

EcoServe: Designing Carbon-Aware AI Inference Systems Deepspeed: System optimizations enable training deep learning models with over 100 billion parameters

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:31:36.488537Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 7448a11e-d57d-4c2d-b208-fb77891febff · outbound

This paper cites Xnnpack: High-performance neural network inference frame- work.

EcoServe: Designing Carbon-Aware AI Inference Systems Xnnpack: High-performance neural network inference frame- work

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:31:36.478285Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 326522fc-a0a5-4117-8891-c16707078f12 · outbound

This paper cites {INFaaS}: Automated model-less inference serving.

EcoServe: Designing Carbon-Aware AI Inference Systems {INFaaS}: Automated model-less inference serving

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:31:36.468500Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 1497fdb9-8396-45d2-a854-6379701e9b70 · outbound

This paper cites BLOOM: A 176B-Parameter Open-Access Multilingual Language Model.

EcoServe: Designing Carbon-Aware AI Inference Systems BLOOM: A 176B-Parameter Open-Access Multilingual Language Model

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-08T20:31:35.783763Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d29ce01-5d38-4f99-aed5-f4e5d6c8ce6a · outbound

This paper cites Life-Cycle Emissions of AI Hardware: A Cradle-To-Grave Approach and Generational Trends.

EcoServe: Designing Carbon-Aware AI Inference Systems Life-Cycle Emissions of AI Hardware: A Cradle-To-Grave Approach and Generational Trends

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-08T20:31:35.787230Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46c1cab4-3d80-42a1-8296-c12421d4113c · outbound

This paper cites Data center lifecycle co2e calculator, 2024.

EcoServe: Designing Carbon-Aware AI Inference Systems Data center lifecycle co2e calculator, 2024

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:31:36.458228Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation aa6744af-cfdd-4370-a6a3-b54261dee034 · outbound

This paper cites an unresolved cited work.

EcoServe: Designing Carbon-Aware AI Inference Systems Unresolved cited work

Reference 68

Resolution: unresolved; raw_fallback, observed 2026-08-08T20:31:36.448776Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 2ddbbc4e-a50a-4c94-8f22-baab846210a6 · outbound

This paper cites Flash reliability in production: The expected and the unexpected.

EcoServe: Designing Carbon-Aware AI Inference Systems Flash reliability in production: The expected and the unexpected

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:31:36.439324Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation d44a77b1-4324-4a47-a29a-fb4912d300d1 · outbound

This paper cites FlexGen: High- Throughput Generative Inference of Large Language Models with a Single GPU.

EcoServe: Designing Carbon-Aware AI Inference Systems FlexGen: High- Throughput Generative Inference of Large Language Models with a Single GPU

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:31:36.429312Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation f8872713-1d1d-4a1c-9467-526027e0dc18 · outbound

This paper cites Lifetime memory reliability data from the field, 2017.

EcoServe: Designing Carbon-Aware AI Inference Systems Lifetime memory reliability data from the field, 2017

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:31:36.418678Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation c8978d1f-3d8f-4ff8-b6ed-06c6ef73bddf · outbound

This paper cites PowerInfer: Fast Large Language Model Serving with a Consumer-grade GPU.

EcoServe: Designing Carbon-Aware AI Inference Systems PowerInfer: Fast Large Language Model Serving with a Consumer-grade GPU

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-08T20:31:35.806995Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f343e95-64d1-48d3-abdf-eb73d1a31f69 · outbound

This paper cites Dynamollm: Designing llm inference clusters for performance and energy effi- ciency.

EcoServe: Designing Carbon-Aware AI Inference Systems Dynamollm: Designing llm inference clusters for performance and energy effi- ciency

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-08T20:31:35.810526Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0a4efb5-8304-4941-a5bb-21f0f7ed3305 · outbound

This paper cites Summarizing CPU and GPU Design Trends with Product Data.

EcoServe: Designing Carbon-Aware AI Inference Systems Summarizing CPU and GPU Design Trends with Product Data

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-08T20:31:35.813779Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd438645-4cef-474d-9dd5-6d29c42177f0 · outbound

This paper cites an unresolved cited work.

EcoServe: Designing Carbon-Aware AI Inference Systems Unresolved cited work

Reference 75

Resolution: unresolved; raw_fallback, observed 2026-08-08T20:31:36.408125Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation ae9d4eb2-618a-49c5-af8f-c318fbc6f526 · outbound

This paper cites Accelerating self-attentions for llm serving with flashinfer, 2024.

EcoServe: Designing Carbon-Aware AI Inference Systems Accelerating self-attentions for llm serving with flashinfer, 2024

Reference 76

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:31:36.396403Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 01203ee5-511f-4a7b-86c4-4be4f6576701 · outbound

This paper cites Micron 1𝛼 dram technology, Nov 2024.

EcoServe: Designing Carbon-Aware AI Inference Systems Micron 1𝛼 dram technology, Nov 2024

Reference 77

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:31:36.385251Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 51ea54c0-3b57-44f7-9511-bfd34df8ddcd · outbound

This paper cites MLPerf Power: Benchmarking the Energy Efficiency of Machine Learning Systems from Microwatts to Megawatts for Sustainable AI.

EcoServe: Designing Carbon-Aware AI Inference Systems MLPerf Power: Benchmarking the Energy Efficiency of Machine Learning Systems from Microwatts to Megawatts for Sustainable AI

Reference 78

Resolution: unresolved; no resolver link, observed 2026-08-08T20:31:35.827403Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3c9782a-5cbc-4116-abe1-c1341b4f5def · outbound

This paper cites vllm v0.6.0: 2.7x throughput improvement and 5x latency reduction, September 2024.

EcoServe: Designing Carbon-Aware AI Inference Systems vllm v0.6.0: 2.7x throughput improvement and 5x latency reduction, September 2024

Reference 79

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:31:36.374458Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 02341d40-c7d6-432c-a6b2-b55baab3415e · outbound

This paper cites Designing cloud servers for lower carbon.

EcoServe: Designing Carbon-Aware AI Inference Systems Designing cloud servers for lower carbon

Reference 80

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:31:36.364131Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation e763be3d-bea8-49f9-bcc6-7c81d6a8f9d7 · outbound

This paper cites Coverage map.

EcoServe: Designing Carbon-Aware AI Inference Systems Coverage map

Reference 81

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:31:36.353608Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation ec1cc89c-0474-4ab7-b452-5cd043f29342 · outbound

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

EcoServe: Designing Carbon-Aware AI Inference Systems Roofline: an insightful visual performance model for multicore architectures

Reference 82

Resolution: unresolved; no resolver link, observed 2026-08-08T20:31:35.841692Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 212090d2-98a2-4f54-ad25-186d776a6d53 · outbound

This paper cites TwinPilots: A New Computing Paradigm for GPU-CPU Parallel LLM Inference.

EcoServe: Designing Carbon-Aware AI Inference Systems TwinPilots: A New Computing Paradigm for GPU-CPU Parallel LLM Inference

Reference 83

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:31:36.336235Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b8426116-bd26-4bef-a19e-3fb5af3b2c1f · outbound

This paper cites Decentralized training of foundation models in heterogeneous environments, 2022.

EcoServe: Designing Carbon-Aware AI Inference Systems Decentralized training of foundation models in heterogeneous environments, 2022

Reference 84

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:31:36.326026Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 2164ac5a-ad2a-4c46-afae-d0fb53ae3d2d · outbound

This paper cites LLM Inference Unveiled: Survey and Roofline Model Insights.

EcoServe: Designing Carbon-Aware AI Inference Systems LLM Inference Unveiled: Survey and Roofline Model Insights

Reference 85

Resolution: unresolved; no resolver link, observed 2026-08-08T20:31:35.852245Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68fc2333-0dd1-4f00-9df2-3087818363af · outbound

This paper cites In 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23) , pages 787–808, 2023.

EcoServe: Designing Carbon-Aware AI Inference Systems In 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23) , pages 787–808, 2023

Reference 86

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:31:36.315196Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 56e64a44-7d99-4188-a2f3-9c4907af8489 · outbound

This paper cites H2o: Heavy- hitter oracle for efficient generative inference of large language models.Advances in Neural Information Processing Systems , 36, 2024.

EcoServe: Designing Carbon-Aware AI Inference Systems H2o: Heavy- hitter oracle for efficient generative inference of large language models.Advances in Neural Information Processing Systems , 36, 2024

Reference 87

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:31:36.304471Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation d679780a-a501-4a46-9f38-09526025853d · outbound

This paper cites HeteGen: Heterogeneous Parallel Inference for Large Language Models on Resource-Constrained Devices.

EcoServe: Designing Carbon-Aware AI Inference Systems HeteGen: Heterogeneous Parallel Inference for Large Language Models on Resource-Constrained Devices

Reference 88

Resolution: unresolved; no resolver link, observed 2026-08-08T20:31:35.863029Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7934aee2-db3f-49ce-9647-c7611e41c361 · outbound

This paper cites SGLang: Efficient Execution of Structured Language Model Programs.

EcoServe: Designing Carbon-Aware AI Inference Systems SGLang: Efficient Execution of Structured Language Model Programs

Reference 89

Resolution: unresolved; no resolver link, observed 2026-08-08T20:31:35.866624Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c1328f7-20fd-4acd-9987-3864e5efbb80 · outbound

This paper cites DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving.

EcoServe: Designing Carbon-Aware AI Inference Systems DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving

Reference 90

Resolution: unresolved; no resolver link, observed 2026-08-08T20:31:35.870375Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation a221b0bb-7cbd-4dd3-a0c6-6230172bd29c · inbound

Cache Your Prompt When It's Green: Carbon-Aware Caching for Large Language Model Serving cites this paper.

Cache Your Prompt When It's Green: Carbon-Aware Caching for Large Language Model Serving EcoServe: Designing Carbon-Aware AI Inference Systems

Reference 40

Resolution: verified exact; arxiv_id, observed 2026-05-19T13:17:18.481714Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b30c03c7-b037-462b-9eb6-cf84d54574c4 · inbound

A Vertical Approach to Designing and Managing Sustainable Heterogeneous Edge Data Centers cites this paper.

A Vertical Approach to Designing and Managing Sustainable Heterogeneous Edge Data Centers EcoServe: Designing Carbon-Aware AI Inference Systems

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T11:39:51.789183Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82f19ffe-d45d-4e31-85bd-68f6e37ec33f · inbound

Quantifying the Energy Consumption and Carbon Emissions of LLM Inference via Simulations cites this paper.

Quantifying the Energy Consumption and Carbon Emissions of LLM Inference via Simulations EcoServe: Designing Carbon-Aware AI Inference Systems

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T17:14:19.340515Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f58870d6-9379-41e0-bfd5-845f567ef1cc · inbound

VoltanaLLM: Energy-Efficient and SLO-Aware Disaggregated LLM Serving via Adaptive Frequency Control and State-Space Routing cites this paper.

VoltanaLLM: Energy-Efficient and SLO-Aware Disaggregated LLM Serving via Adaptive Frequency Control and State-Space Routing EcoServe: Designing Carbon-Aware AI Inference Systems

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-15T16:30:34.981682Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d059cc4-2e94-4531-99cd-cdd635e7bd5a · inbound

Energy-Aware Routing to Large Reasoning Models cites this paper.

Energy-Aware Routing to Large Reasoning Models EcoServe: Designing Carbon-Aware AI Inference Systems

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-16T20:33:24.067155Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 17772232-0efe-498c-bbca-73b5f9903dc5 · inbound

Determinism-Preserving GPU Spatial Sharing with Vitamin-E cites this paper.

Determinism-Preserving GPU Spatial Sharing with Vitamin-E EcoServe: Designing Carbon-Aware AI Inference Systems

Reference 41

Resolution: verified exact; arxiv_id, observed 2026-05-15T10:35:27.451461Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 4b3fa359-f733-408f-a592-3a99a681350a · inbound

KAIROS: Stateful, Context-Aware Power-Efficient Agentic Inference Serving cites this paper.

KAIROS: Stateful, Context-Aware Power-Efficient Agentic Inference Serving EcoServe: Designing Carbon-Aware AI Inference Systems

Reference 35

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T07:01:49.268219Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 56a3eec0-b810-486d-a4d0-121555eb1b26 · inbound

AI Inference as Relocatable Electricity Demand: A Latency-Constrained Energy-Geography Framework cites this paper.

AI Inference as Relocatable Electricity Demand: A Latency-Constrained Energy-Geography Framework EcoServe: Designing Carbon-Aware AI Inference Systems

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-05-12T10:16:27.539416Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 3a610215-e230-4df3-94fb-89a2abfccace · inbound

GAR: Carbon-Aware Routing for LLM Inference via Constrained Optimization cites this paper.

GAR: Carbon-Aware Routing for LLM Inference via Constrained Optimization EcoServe: Designing Carbon-Aware AI Inference Systems

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-13T01:42:03.824803Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 7add184a-0b97-44e2-a689-9a212e1b5ab1 · inbound

Greening AI Inference with Accuracy and Latency-aware User Incentives cites this paper.

Greening AI Inference with Accuracy and Latency-aware User Incentives EcoServe: Designing Carbon-Aware AI Inference Systems

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-06-29T19:03:51.120052Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 0e97ce1d-504d-45a5-a563-baa7ac002d77 · inbound

Evaluation of ML Resource Utilization Requires Model Life Cycle Assessment cites this paper.

Evaluation of ML Resource Utilization Requires Model Life Cycle Assessment EcoServe: Designing Carbon-Aware AI Inference Systems

Reference 67

Resolution: metadata mismatch; arxiv_id, observed 2026-07-01T21:06:14.616536Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 1e29a8b2-ef1e-477e-bdff-e3c98be45dd3 · inbound

From Tokens to Energy Flexibility: Quantization-Enabled Demand Response for Data Centers with LLM Inference Workloads cites this paper.

From Tokens to Energy Flexibility: Quantization-Enabled Demand Response for Data Centers with LLM Inference Workloads EcoServe: Designing Carbon-Aware AI Inference Systems

Reference 29

Resolution: verified exact; arxiv_id, observed 2026-07-04T02:29:23.912557Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 3df9d850-6d9c-429a-bdf5-608747014a6b · inbound

Enabling Spatially Fine-Grained DVFS in Neural Processing Units for Energy-Efficient LLM Serving cites this paper.

Enabling Spatially Fine-Grained DVFS in Neural Processing Units for Energy-Efficient LLM Serving EcoServe: Designing Carbon-Aware AI Inference Systems

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-01T20:57:21.540286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c58e9d3b-f534-4daf-afa9-1372a189abb5 · inbound

Routing LLM Inference to the Cleanest Grid in Real Time cites this paper.

Routing LLM Inference to the Cleanest Grid in Real Time EcoServe: Designing Carbon-Aware AI Inference Systems

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T13:00:30.958563Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb7ba158-1ba9-450c-8a7b-44929659aa1d · inbound

Routing LLM Inference to the Cleanest Grid in Real Time cites this paper.

Routing LLM Inference to the Cleanest Grid in Real Time EcoServe: Designing Carbon-Aware AI Inference Systems

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-07T13:00:31.049555Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.