NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement | Paper Citation Record

Observation 83fd6776-df56-48a6-bb78-7f7eb1130339 · outbound

This paper cites Gulavani, Alexey Tumanov, and Ramachandran Ramjee.

NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement Gulavani, Alexey Tumanov, and Ramachandran Ramjee

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-01T12:00:23.901536Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ff3c4bd-ef9c-4342-b347-2a3ad41f0389 · outbound

This paper cites an unresolved cited work.

NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement Unresolved cited work

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-01T12:00:23.969488Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9754679-c001-4cfd-a2db-c4bb7e1aed2e · outbound

This paper cites an unresolved cited work.

NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement Unresolved cited work

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-01T12:00:24.078454Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 236f11f5-94ae-495f-a6e3-5bd328be44c9 · outbound

This paper cites PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling.

NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-01T12:00:24.193945Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dcdc4c30-2f78-4d60-9033-e2b4e1ac8ab9 · outbound

This paper cites an unresolved cited work.

NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement Unresolved cited work

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-01T12:00:24.294399Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 810f9efd-b7d2-4c6e-85ed-ae8e99ac010b · outbound

This paper cites RetroInfer: A Vector Storage Engine for Scalable Long-Context LLM Inference.

NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement RetroInfer: A Vector Storage Engine for Scalable Long-Context LLM Inference

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-01T12:00:24.299424Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 203f054d-6b15-4be1-a9be-0ff08e39ca10 · outbound

This paper cites an unresolved cited work.

NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement Unresolved cited work

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-01T12:00:24.302792Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40a75209-572d-4ad1-81f0-a9ac5f39846a · outbound

This paper cites an unresolved cited work.

NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement Unresolved cited work

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-01T12:00:24.307341Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e0b8c51c-a00c-48de-a623-7496f68ecd1f · outbound

This paper cites an unresolved cited work.

NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement Unresolved cited work

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-01T12:00:24.309446Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c76fc46-d35b-4af9-bf4a-ee17bbe6722f · outbound

This paper cites an unresolved cited work.

NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement Unresolved cited work

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-01T12:00:24.311404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27a626f1-d55d-48fb-9fc6-c2e0073d4aa9 · outbound

This paper cites an unresolved cited work.

NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement Unresolved cited work

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-01T12:00:24.313658Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f905f3a7-ddb6-4c39-9c3f-e81e238f7fba · outbound

This paper cites an unresolved cited work.

NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement Unresolved cited work

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-01T12:00:24.315757Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b88005c3-2e01-4f00-8afc-65b03062b6ce · outbound

This paper cites an unresolved cited work.

NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement Unresolved cited work

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-01T12:00:24.317922Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b62c0b2-5127-4dd2-b481-a3a2d856862f · outbound

This paper cites RULER: What's the Real Context Size of Your Long-Context Language Models?.

NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement RULER: What's the Real Context Size of Your Long-Context Language Models?

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-01T12:00:24.319890Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3002495a-dfd1-4c50-884c-c698377c527b · outbound

This paper cites an unresolved cited work.

NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement Unresolved cited work

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-01T12:00:24.322021Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 00e0b3c7-e502-4189-8d72-d8b9a7df62af · outbound

This paper cites an unresolved cited work.

NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement Unresolved cited work

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-01T12:00:24.325980Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19fe23ac-298d-469e-ab8c-e7b302339d6d · outbound

This paper cites an unresolved cited work.

NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement Unresolved cited work

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-01T12:00:24.324059Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab96107b-84bf-4d17-8ed6-c66573e40489 · outbound

This paper cites an unresolved cited work.

NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement Unresolved cited work

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-01T12:00:24.330171Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6243ad9-3b48-449e-895e-da5000c597b3 · outbound

This paper cites 2023.𝑆 3: Increasing GPU Utilization during Generative Inference for Higher Throughput.Advances in Neural Information Processing Systems36 (2023), 18015–18027.

NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement 2023.𝑆 3: Increasing GPU Utilization during Generative Inference for Higher Throughput.Advances in Neural Information Processing Systems36 (2023), 18015–18027

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-01T12:00:24.327928Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc252862-98b0-4d58-abdc-784db1f887a5 · outbound

This paper cites an unresolved cited work.

NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement Unresolved cited work

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-01T12:00:24.334822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d91bba64-1cdc-42c5-86b7-c426145681c6 · outbound

This paper cites Lee, Sangdoo Yun, and Hyun Oh Song.

NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement Lee, Sangdoo Yun, and Hyun Oh Song

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-01T12:00:24.332152Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a36f46d6-6f76-4306-8975-f20bd12e4f6c · outbound

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

NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement Gonzalez, Haotong Zhang, and Ion Stoica

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-01T12:00:24.338834Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 769463a6-9a3a-4641-9d7a-6035f015918e · outbound

This paper cites an unresolved cited work.

NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement Unresolved cited work

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-01T12:00:24.336986Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 22415913-043e-48c6-b1b5-eb0060aeac22 · outbound

This paper cites an unresolved cited work.

NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement Unresolved cited work

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-01T12:00:24.342735Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb913c13-1883-4775-99bc-45c9b9785f2c · outbound

This paper cites an unresolved cited work.

NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement Unresolved cited work

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-01T12:00:24.340893Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b6f9911-3cc8-40ae-ae80-f0006ec61775 · outbound

This paper cites an unresolved cited work.

NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement Unresolved cited work

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-01T12:00:24.347608Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02aa21fa-6640-4f94-aaba-94b1af69d49e · outbound

This paper cites an unresolved cited work.

NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement Unresolved cited work

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-01T12:00:24.344739Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 028359ae-f35b-4bfd-a351-0a98f010c251 · outbound

This paper cites an unresolved cited work.

NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement Unresolved cited work

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-01T12:00:24.351865Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 157791a3-fc10-467f-8073-0c4f21e90eb0 · outbound

This paper cites an unresolved cited work.

NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement Unresolved cited work

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-01T12:00:24.349622Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a390197-ab57-4f8a-bc12-a200e6eae55b · outbound

This paper cites an unresolved cited work.

NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement Unresolved cited work

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-01T12:00:24.355778Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 227dc22a-9cc6-4257-ba19-6cef55588081 · outbound

This paper cites an unresolved cited work.

NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement Unresolved cited work

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-01T12:00:24.353700Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0596d7c2-5e46-4fd5-a709-2786388a2ad7 · outbound

This paper cites Concise Thoughts: Impact of Output Length on LLM Reasoning and Cost.

NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement Concise Thoughts: Impact of Output Length on LLM Reasoning and Cost

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-01T12:00:24.359361Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5491e1f-2dd9-4fb9-983d-b0387c9cbe41 · outbound

This paper cites an unresolved cited work.

NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement Unresolved cited work

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-01T12:00:24.357479Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6ee814b-fccc-4e16-b4e3-70d8a61a3c2e · outbound

This paper cites an unresolved cited work.

NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement Unresolved cited work

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-01T12:00:24.363373Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 217f1223-2e3d-4471-9730-f69cbd4d2d03 · outbound

This paper cites an unresolved cited work.

NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement Unresolved cited work

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-01T12:00:24.361398Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2018fec-44bd-47ee-abbe-15e644875153 · outbound

This paper cites an unresolved cited work.

NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement Unresolved cited work

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-01T12:00:24.367407Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36d558ef-bfc5-44bc-88d3-b2e0487f09cd · outbound

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

NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement InstInfer: In-Storage Attention Offloading for Cost-Effective Long-Context LLM Inference

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-01T12:00:24.365208Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d12913ae-b1b3-4e89-9ab7-c64fdf5e8e7a · outbound

This paper cites an unresolved cited work.

NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement Unresolved cited work

Reference 38

Resolution: malformed identifier; no resolver link, observed 2026-08-01T12:00:24.371166Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9724966-8da1-434e-b186-8482e6760397 · outbound

This paper cites an unresolved cited work.

NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement Unresolved cited work

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-01T12:00:24.369264Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ed4195c-747d-40d9-bddc-91eea798e9a4 · outbound

This paper cites an unresolved cited work.

NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement Unresolved cited work

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-01T12:00:24.375165Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4764d7c9-dbd8-4274-9d17-adc5f2b5d85f · outbound

This paper cites an unresolved cited work.

NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement Unresolved cited work

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-01T12:00:24.373272Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 03a28ed4-d9de-41dc-966c-996d8d7639dc · outbound

This paper cites Ezgi Yücel, Jinkwon Kim, José F.

NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement Ezgi Yücel, Jinkwon Kim, José F

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-01T12:00:24.381230Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1086abc8-99a1-4fee-9687-1c3cb3a3a6f7 · outbound

This paper cites an unresolved cited work.

NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement Unresolved cited work

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-01T12:00:24.377010Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 525d3da3-20f4-4d9f-87cd-f68f64dc26b4 · outbound

This paper cites an unresolved cited work.

NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement Unresolved cited work

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-01T12:00:24.385604Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76daa33d-7dd6-43e4-b4da-bf0300038903 · outbound

This paper cites an unresolved cited work.

NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement Unresolved cited work

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-01T12:00:24.387585Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f616160-9dd5-4513-aeea-b0befd3e7ae0 · outbound

This paper cites an unresolved cited work.

NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement Unresolved cited work

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-01T12:00:24.383345Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ac1966d-46cd-420b-812a-c470e9bc929d · outbound

This paper cites an unresolved cited work.

NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement Unresolved cited work

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-01T12:00:24.392350Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8a2c561-c557-44b3-86d6-b2897e98c702 · outbound

This paper cites an unresolved cited work.

NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement Unresolved cited work

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-01T12:00:24.394351Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5dd82064-0bb5-4692-96a9-d38c487f5bc6 · outbound

This paper cites an unresolved cited work.

NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement Unresolved cited work

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-01T12:00:24.389654Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fdfb098c-a60f-4f1f-b4c8-4169a21f77b9 · outbound

This paper cites an unresolved cited work.

NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement Unresolved cited work

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-01T12:00:24.398551Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31550e5b-575f-4795-83f8-d086f1d709cf · outbound

This paper cites an unresolved cited work.

NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement Unresolved cited work

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-01T12:00:24.400733Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca98bd0a-0cc2-4dce-bf16-6ae169906a26 · outbound

This paper cites ServeGen: Workload Characterization and Generation of Large Language Model Serving in Production.

NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement ServeGen: Workload Characterization and Generation of Large Language Model Serving in Production

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-01T12:00:24.396359Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dbb8c55c-7a8a-4c3b-86cf-e384705062ea · outbound

This paper cites an unresolved cited work.

NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement Unresolved cited work

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-01T12:00:24.404330Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b187db27-34d5-4bba-b9fd-d6c8914e1c92 · outbound

This paper cites an unresolved cited work.

NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement Unresolved cited work

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-01T12:00:24.406280Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7242d95-39a6-49f2-aa3a-d2d00b3d9c66 · outbound

This paper cites an unresolved cited work.

NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement Unresolved cited work

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-01T12:00:24.402672Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 03f5a712-6e54-460a-8860-e51a6507d3d6 · outbound

This paper cites an unresolved cited work.

NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement Unresolved cited work

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-01T12:00:24.410109Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d2d8d7c-48a5-4710-a506-4a869d174421 · outbound

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

NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement LLM Inference Unveiled: Survey and Roofline Model Insights

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-01T12:00:24.412238Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ba9aeb0-1222-4cb0-b2b3-0aec095ac74d · outbound

This paper cites an unresolved cited work.

NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement Unresolved cited work

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-01T12:00:24.408161Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa021a8f-fa54-4d5d-9f2b-762b0346dba7 · outbound

This paper cites an unresolved cited work.

NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement Unresolved cited work

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-01T12:00:24.416382Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61173730-87ef-413f-801e-818eb81b8436 · outbound

This paper cites an unresolved cited work.

NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement Unresolved cited work

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-01T12:00:24.418254Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cdca5b8b-fa50-422a-a730-f81d91ac7a93 · outbound

This paper cites an unresolved cited work.

NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement Unresolved cited work

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-01T12:00:24.414489Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49adc9b6-70e5-41a1-9166-ca2de3f5280c · outbound

This paper cites 2024.{DistServe}: Disaggregating prefill and decoding for goodput-optimized large language model serving.

NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement 2024.{DistServe}: Disaggregating prefill and decoding for goodput-optimized large language model serving

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-01T12:00:24.424501Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 609c6c46-bd04-4d1f-b909-c59198a9db17 · outbound

This paper cites Xu, Hao Zhu, Xuhui Zhou, Robert Lo, Abishek Sridhar, Xianyi Cheng, Tianyue Ou, Yonatan Bisk, Daniel Fried, Uri Alon, and Graham Neubig.

NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement Xu, Hao Zhu, Xuhui Zhou, Robert Lo, Abishek Sridhar, Xianyi Cheng, Tianyue Ou, Yonatan Bisk, Daniel Fried, Uri Alon, and Graham Neubig

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-01T12:00:24.426535Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c9d7459-2867-4d94-9199-042a04b142d1 · outbound

This paper cites an unresolved cited work.

NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement Unresolved cited work

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-01T12:00:24.420562Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f829100-cbe4-4ed2-afc6-8ae8a96c8e47 · outbound

This paper cites Fast KV Compaction via Attention Matching.

NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement Fast KV Compaction via Attention Matching

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-01T12:00:24.428630Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8d46ddf-1365-411f-9587-cea71dd504b6 · outbound

This paper cites an unresolved cited work.

NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement Unresolved cited work

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-01T12:00:24.422500Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 37d80edb-c437-45b0-a479-9bac4e60af1c · outbound

This paper cites InInternational Conference on Architectural Support for Programming Languages and Operating Systems.

NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement InInternational Conference on Architectural Support for Programming Languages and Operating Systems

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-01T12:00:24.379152Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7550a55-0728-4e64-8104-1f6220c733bb · outbound

This paper cites ELIS: Efficient LLM Iterative Scheduling System with Response Length Predictor.

NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement ELIS: Efficient LLM Iterative Scheduling System with Response Length Predictor

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-01T12:00:24.304941Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers