Lodestar: An Online-Learning LLM Inference Router | Paper Citation Record

Observation 9f7dd599-168a-4cf0-b45f-b334a535f38d · outbound

This paper cites https://docs.nvidia.com/ dynamo/latest/.

Lodestar: An Online-Learning LLM Inference Router https://docs.nvidia.com/ dynamo/latest/

Reference 1

Resolution: unresolved; no resolver link, observed 2026-06-28T16:55:38.764173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 190a7156-ae26-42bc-8c2f-fb109f879d15 · outbound

This paper cites https: //www.amd.com/en/products/accelerators/ instinct/mi300/mi300a.html, 2023.

Lodestar: An Online-Learning LLM Inference Router https: //www.amd.com/en/products/accelerators/ instinct/mi300/mi300a.html, 2023

Reference 2

Resolution: unresolved; no resolver link, observed 2026-06-28T16:55:38.764173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24e3687e-2f6f-48bc-855d-32af14203f7a · outbound

This paper cites https://sharegpt.com, 2023.

Lodestar: An Online-Learning LLM Inference Router https://sharegpt.com, 2023

Reference 3

Resolution: unresolved; no resolver link, observed 2026-06-28T16:55:38.764173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4fd6016f-04d1-4c93-80c5-7c54bf6a2fb0 · outbound

This paper cites https: //www.nvidia.com/en-us/data-center/ technologies/blackwell-architecture/, 2024.

Lodestar: An Online-Learning LLM Inference Router https: //www.nvidia.com/en-us/data-center/ technologies/blackwell-architecture/, 2024

Reference 4

Resolution: unresolved; no resolver link, observed 2026-06-28T16:55:38.764173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48fda3e4-0676-4de7-8153-3e50d78e51bb · outbound

This paper cites https:// blog.google/products/google-cloud/ ironwood-tpu-age-of-inference/, 2025.

Lodestar: An Online-Learning LLM Inference Router https:// blog.google/products/google-cloud/ ironwood-tpu-age-of-inference/, 2025

Reference 5

Resolution: unresolved; no resolver link, observed 2026-06-28T16:55:38.764173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a479ea20-edd7-45ab-ade5-69527b8cf52e · outbound

This paper cites an unresolved cited work.

Lodestar: An Online-Learning LLM Inference Router Unresolved cited work

Reference 6

Resolution: unresolved; no resolver link, observed 2026-06-28T16:55:38.764173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1056ea5-d11e-451e-8ddc-8055d6c6db02 · outbound

This paper cites an unresolved cited work.

Lodestar: An Online-Learning LLM Inference Router Unresolved cited work

Reference 7

Resolution: unresolved; no resolver link, observed 2026-06-28T16:55:38.764173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad9bd619-381c-44f9-bd11-f76beb1689d9 · outbound

This paper cites https://www.nvidia.

Lodestar: An Online-Learning LLM Inference Router https://www.nvidia

Reference 8

Resolution: unresolved; no resolver link, observed 2026-06-28T16:55:38.764173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca0cac6d-5049-4b39-8bf9-131699c9e227 · outbound

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

Lodestar: An Online-Learning LLM Inference Router Gulavani, Alexey Tu- manov, and Ramachandran Ramjee

Reference 9

Resolution: unresolved; no resolver link, observed 2026-06-28T16:55:38.764173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c929397f-6926-4c31-bb91-84380c8cac1e · outbound

This paper cites Gulavani, and Ramachandran Ramjee.

Lodestar: An Online-Learning LLM Inference Router Gulavani, and Ramachandran Ramjee

Reference 10

Resolution: unresolved; no resolver link, observed 2026-06-28T16:55:38.764173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d6ca5de-04c0-4990-9a18-7392e18f86a3 · outbound

This paper cites Llmrank: Under- standing llm strengths for model routing, 2025.

Lodestar: An Online-Learning LLM Inference Router Llmrank: Under- standing llm strengths for model routing, 2025

Reference 11

Resolution: unresolved; no resolver link, observed 2026-06-28T16:55:38.764173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51d1edb8-a932-4be0-a6ae-786e59a75d06 · outbound

This paper cites Deepspeed inference: Enabling efficient inference of transformer models at unprecedented scale, 2022.

Lodestar: An Online-Learning LLM Inference Router Deepspeed inference: Enabling efficient inference of transformer models at unprecedented scale, 2022

Reference 12

Resolution: unresolved; no resolver link, observed 2026-06-28T16:55:38.764173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c589907a-e087-40c4-ba17-39f7b8bc8ce2 · outbound

This paper cites L-Eval: Insti- tuting standardized evaluation for long context language models, 2023.

Lodestar: An Online-Learning LLM Inference Router L-Eval: Insti- tuting standardized evaluation for long context language models, 2023

Reference 13

Resolution: unresolved; no resolver link, observed 2026-06-28T16:55:38.764173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d55f80d-c599-46e3-bdd7-a82f8fb18a74 · outbound

This paper cites Lee, Deming Chen, and Tri Dao.

Lodestar: An Online-Learning LLM Inference Router Lee, Deming Chen, and Tri Dao

Reference 14

Resolution: unresolved; no resolver link, observed 2026-06-28T16:55:38.764173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe43942d-e2f1-48dc-973a-3028fa51f1ce · outbound

This paper cites FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance.

Lodestar: An Online-Learning LLM Inference Router FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance

Reference 15

Resolution: metadata mismatch; local_arxiv, observed 2026-06-28T17:02:24.562310Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 85419afe-fa21-45fd-acb2-a0cf6012d6fe · outbound

This paper cites {IMPRESS}: An {Importance- Informed}{Multi-Tier} prefix {KV} storage system for large language model inference.

Lodestar: An Online-Learning LLM Inference Router {IMPRESS}: An {Importance- Informed}{Multi-Tier} prefix {KV} storage system for large language model inference

Reference 16

Resolution: unresolved; no resolver link, observed 2026-06-28T16:55:38.764173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2147a59c-35cb-434b-ab12-9c6a5b9719ee · outbound

This paper cites Lmcache: An efficient kv cache layer for enterprise-scale llm inference.

Lodestar: An Online-Learning LLM Inference Router Lmcache: An efficient kv cache layer for enterprise-scale llm inference

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-06-28T17:02:24.549335Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 39ca9c60-8c50-4295-8b11-4ba9f553a169 · outbound

This paper cites Angelopoulos, Tianle Li, Dacheng Li, Banghua Zhu, Hao Zhang, Michael I.

Lodestar: An Online-Learning LLM Inference Router Angelopoulos, Tianle Li, Dacheng Li, Banghua Zhu, Hao Zhang, Michael I

Reference 18

Resolution: unresolved; no resolver link, observed 2026-06-28T16:55:38.764173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a3740445-e3d1-4ecf-9b3e-92bd626f5dc9 · outbound

This paper cites Lmdeploy: A toolkit for com- pressing, deploying, and serving llm.

Lodestar: An Online-Learning LLM Inference Router Lmdeploy: A toolkit for com- pressing, deploying, and serving llm

Reference 19

Resolution: unresolved; no resolver link, observed 2026-06-28T16:55:38.764173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e1bbab2-f7df-425b-9f6f-e61d33b47bd5 · outbound

This paper cites Flashattention: Fast and memory- efficient exact attention with io-awareness.Advances in neural information processing systems, 35:16344– 16359, 2022.

Lodestar: An Online-Learning LLM Inference Router Flashattention: Fast and memory- efficient exact attention with io-awareness.Advances in neural information processing systems, 35:16344– 16359, 2022

Reference 20

Resolution: unresolved; no resolver link, observed 2026-06-28T16:55:38.764173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b882e2f7-ec03-46ab-8647-d525197141ba · outbound

This paper cites Pre- fillonly: An inference engine for prefill-only workloads in large language model applications.

Lodestar: An Online-Learning LLM Inference Router Pre- fillonly: An inference engine for prefill-only workloads in large language model applications

Reference 21

Resolution: unresolved; no resolver link, observed 2026-06-28T16:55:38.764173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 86673f0d-d64f-4f8b-84fc-4f6965eda18a · outbound

This paper cites Turbotransformers: an efficient gpu serving system for transformer models.

Lodestar: An Online-Learning LLM Inference Router Turbotransformers: an efficient gpu serving system for transformer models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-06-28T16:55:38.764173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d6fc379-d2b5-427e-9514-0c4e22900ae5 · outbound

This paper cites Efficient llm scheduling by learn- ing to rank.

Lodestar: An Online-Learning LLM Inference Router Efficient llm scheduling by learn- ing to rank

Reference 23

Resolution: unresolved; no resolver link, observed 2026-06-28T16:55:38.764173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1b6f85b8-045a-46f0-812a-d622a6b04285 · outbound

This paper cites Cost-effective attention reuse across multi-turn conversations in large language model serv- ing.

Lodestar: An Online-Learning LLM Inference Router Cost-effective attention reuse across multi-turn conversations in large language model serv- ing

Reference 24

Resolution: unresolved; no resolver link, observed 2026-06-28T16:55:38.764173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c522d51-e640-4c4d-86d2-e2cccc761687 · outbound

This paper cites Prompt cache: Modular attention reuse for low-latency inference.Pro- ceedings of Machine Learning and Systems, 6:325–338, 2024.

Lodestar: An Online-Learning LLM Inference Router Prompt cache: Modular attention reuse for low-latency inference.Pro- ceedings of Machine Learning and Systems, 6:325–338, 2024

Reference 25

Resolution: unresolved; no resolver link, observed 2026-06-28T16:55:38.764173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17759f6a-02d2-4bb7-b9be-777e62cf6013 · outbound

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

Lodestar: An Online-Learning LLM Inference Router Serving DNNs like clockwork: Performance predictability from the bottom up

Reference 26

Resolution: unresolved; no resolver link, observed 2026-06-28T16:55:38.764173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 055cef4e-f1aa-4688-ad03-158f227f08f0 · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

Lodestar: An Online-Learning LLM Inference Router DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 27

Resolution: verified exact; local_arxiv, observed 2026-06-28T17:02:24.557623Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 1f3ae500-8a88-495f-8716-ff28bf8275d9 · outbound

This paper cites Towards generalized routing: Model and agent orchestration for adaptive and efficient inference, 2025.

Lodestar: An Online-Learning LLM Inference Router Towards generalized routing: Model and agent orchestration for adaptive and efficient inference, 2025

Reference 28

Resolution: unresolved; no resolver link, observed 2026-06-28T16:55:38.764173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5acf9b31-e44a-47fe-b6f2-542f22627a24 · outbound

This paper cites RULER: What’s the real context size of your long-context language models? InFirst Conference on Language Modeling, 2024.

Lodestar: An Online-Learning LLM Inference Router RULER: What’s the real context size of your long-context language models? InFirst Conference on Language Modeling, 2024

Reference 29

Resolution: unresolved; no resolver link, observed 2026-06-28T16:55:38.764173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65d54678-6bab-4544-a354-fc78f5640786 · outbound

This paper cites OpenAI o1 System Card.

Lodestar: An Online-Learning LLM Inference Router OpenAI o1 System Card

Reference 30

Resolution: verified exact; local_arxiv, observed 2026-06-28T17:02:24.559829Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 5a4349a9-6535-4616-b5a4-20ef43dfde06 · outbound

This paper cites Gonza- lez, Hao Zhang, and Ion Stoica.

Lodestar: An Online-Learning LLM Inference Router Gonza- lez, Hao Zhang, and Ion Stoica

Reference 31

Resolution: unresolved; no resolver link, observed 2026-06-28T16:55:38.764173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa873f7c-f135-4aef-8d40-e1c0a05a4f64 · outbound

This paper cites InfiniGen: Efficient generative inference of large language models with dynamic KV cache management.

Lodestar: An Online-Learning LLM Inference Router InfiniGen: Efficient generative inference of large language models with dynamic KV cache management

Reference 32

Resolution: unresolved; no resolver link, observed 2026-06-28T16:55:38.764173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e96d14a-d539-4cd9-bae1-2b39a1d9d862 · outbound

This paper cites Fast inference from transformers via speculative decoding.

Lodestar: An Online-Learning LLM Inference Router Fast inference from transformers via speculative decoding

Reference 33

Resolution: unresolved; no resolver link, observed 2026-06-28T16:55:38.764173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4794d1b5-6320-4c98-a69b-a557df98b478 · outbound

This paper cites LooGLE: Can long-context language models understand long contexts?, 2023.

Lodestar: An Online-Learning LLM Inference Router LooGLE: Can long-context language models understand long contexts?, 2023

Reference 34

Resolution: unresolved; no resolver link, observed 2026-06-28T16:55:38.764173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98b445e0-3438-4855-bffa-b2663de4b2e6 · outbound

This paper cites Eagle: speculative sampling requires rethinking feature uncertainty.

Lodestar: An Online-Learning LLM Inference Router Eagle: speculative sampling requires rethinking feature uncertainty

Reference 35

Resolution: unresolved; no resolver link, observed 2026-06-28T16:55:38.764173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cedb02ee-7bd4-4086-b802-149f6f69fb6c · outbound

This paper cites Opportunities and challenges in service layer traffic engineering.

Lodestar: An Online-Learning LLM Inference Router Opportunities and challenges in service layer traffic engineering

Reference 36

Resolution: unresolved; no resolver link, observed 2026-06-28T16:55:38.764173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82069fb6-7952-48ab-b879-fcb3427066b8 · outbound

This paper cites KV-Cache Indexer: Architecture.

Lodestar: An Online-Learning LLM Inference Router KV-Cache Indexer: Architecture

Reference 37

Resolution: unresolved; no resolver link, observed 2026-06-28T16:55:38.764173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e221b453-dbd2-4f84-b55c-9c0ea4890778 · outbound

This paper cites Helix: Serving large language models over heterogeneous gpus and net- work via max-flow.

Lodestar: An Online-Learning LLM Inference Router Helix: Serving large language models over heterogeneous gpus and net- work via max-flow

Reference 38

Resolution: unresolved; no resolver link, observed 2026-06-28T16:55:38.764173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20f5535f-5f0c-4fd4-bd60-749185cfbce6 · outbound

This paper cites Mitzenmacher.

Lodestar: An Online-Learning LLM Inference Router Mitzenmacher

Reference 39

Resolution: unresolved; no resolver link, observed 2026-06-28T16:55:38.764173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5e66b18-7c11-46d6-8934-1ecfbeda1a50 · outbound

This paper cites Heterogeneity-aware cluster scheduling policies for deep learning workloads.

Lodestar: An Online-Learning LLM Inference Router Heterogeneity-aware cluster scheduling policies for deep learning workloads

Reference 40

Resolution: unresolved; no resolver link, observed 2026-06-28T16:55:38.764173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b780eadb-ea65-4bd3-9c02-5d50ef0e6615 · outbound

This paper cites Fastertransformer.

Lodestar: An Online-Learning LLM Inference Router Fastertransformer

Reference 41

Resolution: unresolved; no resolver link, observed 2026-06-28T16:55:38.764173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4af8685-210a-4673-ba4b-ae5ba9b37bb3 · outbound

This paper cites Dynamo kv-aware router.

Lodestar: An Online-Learning LLM Inference Router Dynamo kv-aware router

Reference 42

Resolution: unresolved; no resolver link, observed 2026-06-28T16:55:38.764173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5287d493-bb4f-4427-879d-058d9c70b93f · outbound

This paper cites Gonzalez, M Waleed Kadous, and Ion Stoica.

Lodestar: An Online-Learning LLM Inference Router Gonzalez, M Waleed Kadous, and Ion Stoica

Reference 43

Resolution: unresolved; no resolver link, observed 2026-06-28T16:55:38.764173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6e73064-1291-42f8-8f6b-c333f898fe91 · outbound

This paper cites Mar- coni: Prefix caching for the era of hybrid llms, 2025.

Lodestar: An Online-Learning LLM Inference Router Mar- coni: Prefix caching for the era of hybrid llms, 2025

Reference 44

Resolution: unresolved; no resolver link, observed 2026-06-28T16:55:38.764173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93d98791-af58-4947-a6a0-7b9d7ed33313 · outbound

This paper cites Prefill-as-a-service: Kvcache of next-generation models could go cross-datacenter, 2026.

Lodestar: An Online-Learning LLM Inference Router Prefill-as-a-service: Kvcache of next-generation models could go cross-datacenter, 2026

Reference 45

Resolution: unresolved; no resolver link, observed 2026-06-28T16:55:38.764173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c4297fe-f408-4521-9957-4ed5fe7e9d3e · outbound

This paper cites Mooncake: Trading more storage for less computation — a KVCache-centric architecture for serving LLM chatbot.

Lodestar: An Online-Learning LLM Inference Router Mooncake: Trading more storage for less computation — a KVCache-centric architecture for serving LLM chatbot

Reference 46

Resolution: unresolved; no resolver link, observed 2026-06-28T16:55:38.764173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4612b1b2-40eb-409d-a22f-ea62176fa68c · outbound

This paper cites A reduction of imitation learning and structured prediction to no-regret online learning.

Lodestar: An Online-Learning LLM Inference Router A reduction of imitation learning and structured prediction to no-regret online learning

Reference 47

Resolution: unresolved; no resolver link, observed 2026-06-28T16:55:38.764173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8abb5e58-9a2f-45bc-8e41-9bcbc798ee3e · outbound

This paper cites Dynaserve: Unified and elastic execution for dynamic disaggregated llm serving, 2025.

Lodestar: An Online-Learning LLM Inference Router Dynaserve: Unified and elastic execution for dynamic disaggregated llm serving, 2025

Reference 48

Resolution: unresolved; no resolver link, observed 2026-06-28T16:55:38.764173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ca3c0c0-4d2a-4853-ade6-8eceea901812 · outbound

This paper cites Campbell, Aditya Akella, Christopher J.

Lodestar: An Online-Learning LLM Inference Router Campbell, Aditya Akella, Christopher J

Reference 49

Resolution: unresolved; no resolver link, observed 2026-06-28T16:55:38.764173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ada47784-d3be-4e00-9aa3-939c6efa2be9 · outbound

This paper cites Aibrix: Towards scalable, cost-effective large language model inference infrastructure, 2025.

Lodestar: An Online-Learning LLM Inference Router Aibrix: Towards scalable, cost-effective large language model inference infrastructure, 2025

Reference 50

Resolution: unresolved; no resolver link, observed 2026-06-28T16:55:38.764173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ebc635f-8421-4801-bfb7-fa3336cdc759 · outbound

This paper cites Preble: Efficient distributed prompt scheduling for llm serving, 2024.

Lodestar: An Online-Learning LLM Inference Router Preble: Efficient distributed prompt scheduling for llm serving, 2024

Reference 51

Resolution: unresolved; no resolver link, observed 2026-06-28T16:55:38.764173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b1e04f9-3c62-4630-b2d2-efb2d9060953 · outbound

This paper cites C3: Cutting tail latency in cloud data stores via adaptive replica selection.

Lodestar: An Online-Learning LLM Inference Router C3: Cutting tail latency in cloud data stores via adaptive replica selection

Reference 52

Resolution: unresolved; no resolver link, observed 2026-06-28T16:55:38.764173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3fc3ce4f-aaed-4b43-b981-eedc271ef35d · outbound

This paper cites AIBrix Gateway: Pre- fix Cache and Load-Aware Routing.

Lodestar: An Online-Learning LLM Inference Router AIBrix Gateway: Pre- fix Cache and Load-Aware Routing

Reference 53

Resolution: unresolved; no resolver link, observed 2026-06-28T16:55:38.764173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e345937a-b83c-48fd-b915-d87576571e0e · outbound

This paper cites an unresolved cited work.

Lodestar: An Online-Learning LLM Inference Router Unresolved cited work

Reference 54

Resolution: unresolved; no resolver link, observed 2026-06-28T16:55:38.764173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8640fdd2-5c02-4d10-9fe4-c3a137768e46 · outbound

This paper cites SGLang model gate- way: prefix_hash routing policy.

Lodestar: An Online-Learning LLM Inference Router SGLang model gate- way: prefix_hash routing policy

Reference 55

Resolution: unresolved; no resolver link, observed 2026-06-28T16:55:38.764173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 670a084f-13b7-4ab0-8038-305efdcfc822 · outbound

This paper cites GCR: Gradient coreset based re- play buffer selection for continual learning.

Lodestar: An Online-Learning LLM Inference Router GCR: Gradient coreset based re- play buffer selection for continual learning

Reference 56

Resolution: unresolved; no resolver link, observed 2026-06-28T16:55:38.764173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6f083d1-1100-4d28-9889-90e76f050c6e · outbound

This paper cites vllm seman- tic router.

Lodestar: An Online-Learning LLM Inference Router vllm seman- tic router

Reference 57

Resolution: unresolved; no resolver link, observed 2026-06-28T16:55:38.764173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d9ed94db-cdac-4a23-9cd0-70e47834b267 · outbound

This paper cites Kvcache cache in the wild: Char- acterizing and optimizing kvcache cache at a large cloud provider.

Lodestar: An Online-Learning LLM Inference Router Kvcache cache in the wild: Char- acterizing and optimizing kvcache cache at a large cloud provider

Reference 58

Resolution: unresolved; no resolver link, observed 2026-06-28T16:55:38.764173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38e3bb4d-7a66-4493-afca-66643d3f92db · outbound

This paper cites Hetis: Serving LLMs in Heterogeneous GPU Clusters with Fine-grained and Dynamic Parallelism.

Lodestar: An Online-Learning LLM Inference Router Hetis: Serving LLMs in Heterogeneous GPU Clusters with Fine-grained and Dynamic Parallelism

Reference 59

Resolution: verified exact; arxiv_id, observed 2026-06-28T17:02:24.555133Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 2b2819f6-a766-4164-912d-ae396f199382 · outbound

This paper cites MLaaS in the wild: Workload analysis and scheduling in large-scale heterogeneous GPU clus- ters.

Lodestar: An Online-Learning LLM Inference Router MLaaS in the wild: Workload analysis and scheduling in large-scale heterogeneous GPU clus- ters

Reference 60

Resolution: unresolved; no resolver link, observed 2026-06-28T16:55:38.764173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05e0ed30-c358-4b29-9e7f-d4d318e45bb4 · outbound

This paper cites Fast distributed inference serving for large language models, 2024.

Lodestar: An Online-Learning LLM Inference Router Fast distributed inference serving for large language models, 2024

Reference 61

Resolution: unresolved; no resolver link, observed 2026-06-28T16:55:38.764173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c47311ce-efc5-496e-8bfd-636041df4c50 · outbound

This paper cites Deserve: Towards affordable offline llm inference via decentralization, 2025.

Lodestar: An Online-Learning LLM Inference Router Deserve: Towards affordable offline llm inference via decentralization, 2025

Reference 62

Resolution: unresolved; no resolver link, observed 2026-06-28T16:55:38.764173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05ee2cbb-5abb-45e3-893d-368014039462 · outbound

This paper cites Rum- ble, and Aaron Archer.

Lodestar: An Online-Learning LLM Inference Router Rum- ble, and Aaron Archer

Reference 63

Resolution: unresolved; no resolver link, observed 2026-06-28T16:55:38.764173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e3d61e0b-d6b7-46e0-8b5e-788e6e1d3500 · outbound

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

Lodestar: An Online-Learning LLM Inference Router Towards Efficient and Practical GPU Multitasking in the Era of LLM

Reference 64

Resolution: verified exact; arxiv_id, observed 2026-06-28T17:02:24.559538Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 01b6bb0e-0428-4928-9221-6553eb7016fd · outbound

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

Lodestar: An Online-Learning LLM Inference Router Orca: A distributed serving system for Transformer-Based generative mod- els

Reference 65

Resolution: unresolved; no resolver link, observed 2026-06-28T16:55:38.764173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42673797-0ccd-42bd-983b-6fee4797fffd · outbound

This paper cites Prism: Cost-Efficient Multi-LLM Serving via GPU Memory Ballooning.

Lodestar: An Online-Learning LLM Inference Router Prism: Cost-Efficient Multi-LLM Serving via GPU Memory Ballooning

Reference 66

Resolution: verified exact; local_arxiv, observed 2026-06-28T17:02:24.546059Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 0d267371-f70c-480c-962c-75eaec5c2d82 · outbound

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

Lodestar: An Online-Learning LLM Inference Router Gonzalez, Ion Stoica, and Hao Zhang

Reference 67

Resolution: unresolved; no resolver link, observed 2026-06-28T16:55:38.764173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d2f0d1f-3605-4787-96ff-95db13dea2ca · outbound

This paper cites Gonzalez, Clark Bar- rett, and Ying Sheng.

Lodestar: An Online-Learning LLM Inference Router Gonzalez, Clark Bar- rett, and Ying Sheng

Reference 68

Resolution: unresolved; no resolver link, observed 2026-06-28T16:55:38.764173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e3bbbe73-3f06-42a9-8ff9-f5359946746a · outbound

This paper cites Dist- serve: disaggregating prefill and decoding for goodput- optimized large language model serving.

Lodestar: An Online-Learning LLM Inference Router Dist- serve: disaggregating prefill and decoding for goodput- optimized large language model serving

Reference 69

Resolution: unresolved; no resolver link, observed 2026-06-28T16:55:38.764173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4284b26d-ad33-40c0-b6a2-18c6630bfce8 · outbound

This paper cites NanoFlow: Towards optimal large language model serving through- put.

Lodestar: An Online-Learning LLM Inference Router NanoFlow: Towards optimal large language model serving through- put

Reference 70

Resolution: unresolved; no resolver link, observed 2026-06-28T16:55:38.764173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 820e302b-728c-4eb3-bc88-a401534a9313 · outbound

This paper cites an unresolved cited work.

Lodestar: An Online-Learning LLM Inference Router Unresolved cited work

Reference 71

Resolution: unresolved; no resolver link, observed 2026-06-28T16:55:38.764173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc6439f7-3c9c-4829-9d77-69565faf5d48 · outbound

This paper cites an unresolved cited work.

Lodestar: An Online-Learning LLM Inference Router Unresolved cited work

Reference 72

Resolution: unresolved; no resolver link, observed 2026-06-28T16:55:38.764173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58538f88-857b-43d9-98a4-b1b7c2afd3c1 · outbound

This paper cites an unresolved cited work.

Lodestar: An Online-Learning LLM Inference Router Unresolved cited work

Reference 73

Resolution: unresolved; no resolver link, observed 2026-06-28T16:55:38.764173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aead39e7-0333-471e-b78d-49076ff277b3 · outbound

This paper cites bitsandbytes is a popular on-the-fly quantization method that compress FP16 KV into INT4/INT8 when storing them.

Lodestar: An Online-Learning LLM Inference Router bitsandbytes is a popular on-the-fly quantization method that compress FP16 KV into INT4/INT8 when storing them

Reference 74

Resolution: unresolved; no resolver link, observed 2026-06-28T16:55:38.764173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers