Paper Citation Record · LEDGER

SeaLLM: Service-Aware and Latency-Optimized Resource Sharing for Large Language Model Inference

As of 19 August 2026, this Paper Citation Record lists 56 of 56 outbound references and 3 inbound Pith citation observations for arXiv:2504.15720.

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

pith.paper-citation-record.v1
2504.15720 v1

Coverage vector

measured 56 of 56 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-16T11:27:17.414952Z

measured 59 of 59 standing notices

One-hop event checks from named stored sources.

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

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-21T08:39:31.911497Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-21T08:39:53.273252Z

Reference resolution

56 of 56 outbound references displayed

verified exact1
verified fuzzy40
unresolved15
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 7340987e-080f-449a-9a66-6ac0cdbe4ecc · outbound

This paper cites https://github.com/NVIDIA/ FasterTransformer, 2019.

SeaLLM: Service-Aware and Latency-Optimized Resource Sharing for Large Language Model Inference https://github.com/NVIDIA/ FasterTransformer, 2019

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:27:18.437702Z

Source-reported events for the cited work

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

Observation 6137fcf8-0bf5-47cf-a180-f172b67436dc · outbound

This paper cites https://grpc.io, 2021.

SeaLLM: Service-Aware and Latency-Optimized Resource Sharing for Large Language Model Inference https://grpc.io, 2021

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:27:18.422918Z

Source-reported events for the cited work

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

Observation bfe8ab4c-5883-4dae-bdd5-b7c2a033375e · outbound

This paper cites https://github.com/intel/ Multi-llms-Chatbot-CloudNative-LangChain , 2022.

SeaLLM: Service-Aware and Latency-Optimized Resource Sharing for Large Language Model Inference https://github.com/intel/ Multi-llms-Chatbot-CloudNative-LangChain , 2022

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:27:18.407689Z

Source-reported events for the cited work

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

Observation 7cb0b10c-5c72-42c7-820a-23ae4df85cd2 · outbound

This paper cites https://docs.nvidia.com/ deploy/mps/index.html, 2022.

SeaLLM: Service-Aware and Latency-Optimized Resource Sharing for Large Language Model Inference https://docs.nvidia.com/ deploy/mps/index.html, 2022

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:27:18.392475Z

Source-reported events for the cited work

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

Observation f8e2f591-8374-4098-a8a6-4f439e3d9f51 · outbound

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

SeaLLM: Service-Aware and Latency-Optimized Resource Sharing for Large Language Model Inference https://sharegpt.com/, 2023

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:27:18.377688Z

Source-reported events for the cited work

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

Observation 0e2ffc21-970c-4021-ad09-c809c8a3fd76 · outbound

This paper cites https://github.com/NVIDIA/ TensorRT-LLM, 2023.

SeaLLM: Service-Aware and Latency-Optimized Resource Sharing for Large Language Model Inference https://github.com/NVIDIA/ TensorRT-LLM, 2023

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:27:18.362918Z

Source-reported events for the cited work

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

Observation 30ee97f0-454d-4498-a683-085927b9d4cf · outbound

This paper cites https://github.com/ huggingface/text-generation-inference, 2023.

SeaLLM: Service-Aware and Latency-Optimized Resource Sharing for Large Language Model Inference https://github.com/ huggingface/text-generation-inference, 2023

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:27:18.348008Z

Source-reported events for the cited work

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

Observation 3f08bd48-9ae9-407b-8dae-d6a497397c42 · outbound

This paper cites GPT-4 Technical Report.

SeaLLM: Service-Aware and Latency-Optimized Resource Sharing for Large Language Model Inference GPT-4 Technical Report

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-16T11:27:17.199332Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 86a07eb9-9c87-4048-8481-745792a8a018 · outbound

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

SeaLLM: Service-Aware and Latency-Optimized Resource Sharing for Large Language Model Inference SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-16T11:27:17.203985Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d05bb618-29ef-4a9e-a683-2da7b9daee7d · outbound

This paper cites pfabric: Minimal near-optimal datacenter transport.

SeaLLM: Service-Aware and Latency-Optimized Resource Sharing for Large Language Model Inference pfabric: Minimal near-optimal datacenter transport

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:27:18.332789Z

Source-reported events for the cited work

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

Observation 45ceae2e-00af-42c3-8b54-fa97901524c5 · outbound

This paper cites Deepspeed-inference: enabling efficient inference of transformer models at unprecedented scale.

SeaLLM: Service-Aware and Latency-Optimized Resource Sharing for Large Language Model Inference Deepspeed-inference: enabling efficient inference of transformer models at unprecedented scale

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:27:18.317402Z

Source-reported events for the cited work

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

Observation 74150bb5-c2f8-4f96-b4b7-3924b8695457 · outbound

This paper cites LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding.

SeaLLM: Service-Aware and Latency-Optimized Resource Sharing for Large Language Model Inference LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-16T11:27:17.217764Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a423f4c-22be-4540-b5c4-3b861345263b · outbound

This paper cites Language models are few-shot learners.

SeaLLM: Service-Aware and Latency-Optimized Resource Sharing for Large Language Model Inference Language models are few-shot learners

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:27:18.302016Z

Source-reported events for the cited work

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

Observation 12a6f59a-544e-4085-804c-2856e0574a86 · outbound

This paper cites Round-robin syn- chronization: Mitigating communication bottlenecks in parameter servers.

SeaLLM: Service-Aware and Latency-Optimized Resource Sharing for Large Language Model Inference Round-robin syn- chronization: Mitigating communication bottlenecks in parameter servers

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:27:18.287280Z

Source-reported events for the cited work

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

Observation 108fd049-8043-4ddb-8568-ed22aa21b78f · outbound

This paper cites Evaluating Large Language Models Trained on Code.

SeaLLM: Service-Aware and Latency-Optimized Resource Sharing for Large Language Model Inference Evaluating Large Language Models Trained on Code

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-16T11:27:17.232360Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ae1a0f0-9cc4-4839-9fe7-67b4416419a4 · outbound

This paper cites Gonzalez, Ion Sto- ica, and Eric P.

SeaLLM: Service-Aware and Latency-Optimized Resource Sharing for Large Language Model Inference Gonzalez, Ion Sto- ica, and Eric P

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:27:18.273477Z

Source-reported events for the cited work

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

Observation ebed2ad7-3604-4734-ab14-18343632a9ba · outbound

This paper cites Fu, Stefano Ermon, Atri Rudra, and Christopher Ré.

SeaLLM: Service-Aware and Latency-Optimized Resource Sharing for Large Language Model Inference Fu, Stefano Ermon, Atri Rudra, and Christopher Ré

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:27:18.260324Z

Source-reported events for the cited work

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

Observation 4aca20fb-7ba0-4821-a637-cfb9847e78cf · outbound

This paper cites Muxserve: Flexible spatial-temporal multiplex- ing for multiple llm serving.

SeaLLM: Service-Aware and Latency-Optimized Resource Sharing for Large Language Model Inference Muxserve: Flexible spatial-temporal multiplex- ing for multiple llm serving

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:27:18.245593Z

Source-reported events for the cited work

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

Observation 64b2057c-11b8-4c18-9e0e-77cd9ccde5b3 · outbound

This paper cites The Llama 3 Herd of Models.

SeaLLM: Service-Aware and Latency-Optimized Resource Sharing for Large Language Model Inference The Llama 3 Herd of Models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-16T11:27:17.251005Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 964531ed-3e3d-4bc5-a3d5-2105cfc0a74d · outbound

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

SeaLLM: Service-Aware and Latency-Optimized Resource Sharing for Large Language Model Inference Turbotransformers: an efficient gpu serving system for transformer models

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:27:18.230830Z

Source-reported events for the cited work

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

Observation 561bcb60-52e4-4e30-8242-52a98e2b0249 · outbound

This paper cites Elasticflow: An elastic server- less training platform for distributed deep learning.

SeaLLM: Service-Aware and Latency-Optimized Resource Sharing for Large Language Model Inference Elasticflow: An elastic server- less training platform for distributed deep learning

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:27:18.215724Z

Source-reported events for the cited work

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

Observation ca31ddfd-51f7-4a7e-8a9a-c8f5cfa0e6e4 · outbound

This paper cites Microsecond-scale preemption for concurrent gpu-accelerated dnn inferences.

SeaLLM: Service-Aware and Latency-Optimized Resource Sharing for Large Language Model Inference Microsecond-scale preemption for concurrent gpu-accelerated dnn inferences

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:27:18.199737Z

Source-reported events for the cited work

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

Observation d2c85ef4-c9e7-4393-b965-2be97d35296d · outbound

This paper cites DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference.

SeaLLM: Service-Aware and Latency-Optimized Resource Sharing for Large Language Model Inference DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-16T11:27:17.268072Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac7f61a9-07fa-4315-b3e7-bb5ad79f5fec · outbound

This paper cites Flashdecod- ing++: Faster large language model inference with asyn- chronization, flat gemm optimization, and heuristics.

SeaLLM: Service-Aware and Latency-Optimized Resource Sharing for Large Language Model Inference Flashdecod- ing++: Faster large language model inference with asyn- chronization, flat gemm optimization, and heuristics

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:27:18.184577Z

Source-reported events for the cited work

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

Observation e2a3d4bc-076a-42b9-bf77-696f2ed63a25 · outbound

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

SeaLLM: Service-Aware and Latency-Optimized Resource Sharing for Large Language Model Inference Inference without Interference: Disaggregate LLM Inference for Mixed Downstream Workloads

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-16T11:27:17.277341Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7719e71-a5ac-471e-8d7e-3d7c26213d34 · outbound

This paper cites Gpipe: Effi- cient training of giant neural networks using pipeline parallelism.

SeaLLM: Service-Aware and Latency-Optimized Resource Sharing for Large Language Model Inference Gpipe: Effi- cient training of giant neural networks using pipeline parallelism

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:27:18.168562Z

Source-reported events for the cited work

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

Observation ecc4599a-b499-46bf-b337-5d25da035521 · outbound

This paper cites Shinjuku: Preemptive scheduling for µsecond-scale tail latency.

SeaLLM: Service-Aware and Latency-Optimized Resource Sharing for Large Language Model Inference Shinjuku: Preemptive scheduling for µsecond-scale tail latency

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:27:18.153806Z

Source-reported events for the cited work

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

Observation 290c8da1-53d9-4015-94fb-2ea69faa371a · outbound

This paper cites Reducing activation recomputation in large transformer models.

SeaLLM: Service-Aware and Latency-Optimized Resource Sharing for Large Language Model Inference Reducing activation recomputation in large transformer models

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:27:18.138872Z

Source-reported events for the cited work

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

Observation 13a05f4b-25dc-4ac6-9aaa-230fb6bc8c73 · outbound

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

SeaLLM: Service-Aware and Latency-Optimized Resource Sharing for Large Language Model Inference Gonza- lez, Hao Zhang, and Ion Stoica

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:27:18.123732Z

Source-reported events for the cited work

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

Observation 15d34d5a-454c-40b0-a7d4-a61e1350e5fc · outbound

This paper cites Sequence parallelism: Long sequence training from system perspective.

SeaLLM: Service-Aware and Latency-Optimized Resource Sharing for Large Language Model Inference Sequence parallelism: Long sequence training from system perspective

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:27:18.109417Z

Source-reported events for the cited work

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

Observation 993a94d8-7221-492f-b46e-c519cac68129 · outbound

This paper cites Competition-level code generation with alphacode.

SeaLLM: Service-Aware and Latency-Optimized Resource Sharing for Large Language Model Inference Competition-level code generation with alphacode

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:27:18.094156Z

Source-reported events for the cited work

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

Observation 3b3d3043-2aeb-4426-aba0-bfea757543cd · outbound

This paper cites Alpaserve: Sta- tistical multiplexing with model parallelism for deep learning serving.

SeaLLM: Service-Aware and Latency-Optimized Resource Sharing for Large Language Model Inference Alpaserve: Sta- tistical multiplexing with model parallelism for deep learning serving

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:27:18.079789Z

Source-reported events for the cited work

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

Observation 7af6f457-8d82-43b7-a81d-c976d297061c · outbound

This paper cites Terapipe: Token-level pipeline parallelism for training large-scale language models.

SeaLLM: Service-Aware and Latency-Optimized Resource Sharing for Large Language Model Inference Terapipe: Token-level pipeline parallelism for training large-scale language models

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:27:18.064680Z

Source-reported events for the cited work

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

Observation 24f35d1e-0f34-4aa3-8a44-83907a6554a9 · outbound

This paper cites Zico: Efficient gpu memory sharing for concurrent dnn training.

SeaLLM: Service-Aware and Latency-Optimized Resource Sharing for Large Language Model Inference Zico: Efficient gpu memory sharing for concurrent dnn training

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:27:18.048956Z

Source-reported events for the cited work

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

Observation 10393a52-3a95-41f3-9c7c-3d58ce127f58 · outbound

This paper cites Pipedream: Gen- eralized pipeline parallelism for dnn training.

SeaLLM: Service-Aware and Latency-Optimized Resource Sharing for Large Language Model Inference Pipedream: Gen- eralized pipeline parallelism for dnn training

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:27:18.033732Z

Source-reported events for the cited work

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

Observation 1c598833-6275-46a8-a4b4-14eaddbebf7b · outbound

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

SeaLLM: Service-Aware and Latency-Optimized Resource Sharing for Large Language Model Inference Splitwise: Efficient generative llm inference using phase splitting

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:27:18.018424Z

Source-reported events for the cited work

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

Observation 680c6e61-5bc9-4070-9d7e-59aeacb5e1e8 · outbound

This paper cites Efficiently scal- ing transformer inference.

SeaLLM: Service-Aware and Latency-Optimized Resource Sharing for Large Language Model Inference Efficiently scal- ing transformer inference

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:27:18.002764Z

Source-reported events for the cited work

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

Observation a6758c99-b124-4416-8159-45e92a8712b3 · outbound

This paper cites Zero: Memory optimizations toward train- ing trillion parameter models.

SeaLLM: Service-Aware and Latency-Optimized Resource Sharing for Large Language Model Inference Zero: Memory optimizations toward train- ing trillion parameter models

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:27:17.987739Z

Source-reported events for the cited work

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

Observation 418eeff4-2bb2-44d8-8635-3d86d76ec71a · outbound

This paper cites Serverless in the wild: Characterizing and optimizing the serverless workload at a large cloud provider.

SeaLLM: Service-Aware and Latency-Optimized Resource Sharing for Large Language Model Inference Serverless in the wild: Characterizing and optimizing the serverless workload at a large cloud provider

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:27:17.972262Z

Source-reported events for the cited work

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

Observation 28abbef3-c935-4056-99c5-e7b03e64a3c1 · outbound

This paper cites Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism.

SeaLLM: Service-Aware and Latency-Optimized Resource Sharing for Large Language Model Inference Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-16T11:27:17.344593Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 686fb88e-7559-4346-b6b9-d5b9663b7f76 · outbound

This paper cites Llm-planner: Few-shot grounded planning for embodied agents with large language models.

SeaLLM: Service-Aware and Latency-Optimized Resource Sharing for Large Language Model Inference Llm-planner: Few-shot grounded planning for embodied agents with large language models

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:27:17.956997Z

Source-reported events for the cited work

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

Observation b6110508-98e0-496b-b71e-c1b844c56dbd · outbound

This paper cites Dynamollm: Designing llm inference clusters for performance and energy efficiency.

SeaLLM: Service-Aware and Latency-Optimized Resource Sharing for Large Language Model Inference Dynamollm: Designing llm inference clusters for performance and energy efficiency

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-16T11:27:17.353326Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6e4fa56-6336-48b4-851b-aa1407346ef2 · outbound

This paper cites Llumnix: Dynamic scheduling for large language model serving.

SeaLLM: Service-Aware and Latency-Optimized Resource Sharing for Large Language Model Inference Llumnix: Dynamic scheduling for large language model serving

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:27:17.941685Z

Source-reported events for the cited work

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

Observation 178d2813-11b0-4bd9-9b3e-677066d2c086 · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

SeaLLM: Service-Aware and Latency-Optimized Resource Sharing for Large Language Model Inference Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-16T11:27:17.361613Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80e70e61-a666-41bf-8b35-1fd428345ac4 · outbound

This paper cites Finding Optimal Policy for Queueing Models: New Parameterization.

SeaLLM: Service-Aware and Latency-Optimized Resource Sharing for Large Language Model Inference Finding Optimal Policy for Queueing Models: New Parameterization

Reference 45

Resolution: verified exact; local_arxiv, observed 2026-08-16T11:27:17.534781Z

Source-reported events for the cited work

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

Observation 303f878a-d1b0-453a-adb6-f66e547d35bb · outbound

This paper cites Dynamic scheduling with convex delay costs: The generalized c| mu rule.

SeaLLM: Service-Aware and Latency-Optimized Resource Sharing for Large Language Model Inference Dynamic scheduling with convex delay costs: The generalized c| mu rule

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:27:17.924984Z

Source-reported events for the cited work

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

Observation e519926c-c0b5-4239-a092-d6b098a22f3f · outbound

This paper cites LightSeq: A High Performance Inference Library for Transformers.

SeaLLM: Service-Aware and Latency-Optimized Resource Sharing for Large Language Model Inference LightSeq: A High Performance Inference Library for Transformers

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-16T11:27:17.373953Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4124632a-afae-4454-b462-ec55e7c25d5c · outbound

This paper cites BurstGPT: A Real-world Workload Dataset to Optimize LLM Serving Systems.

SeaLLM: Service-Aware and Latency-Optimized Resource Sharing for Large Language Model Inference BurstGPT: A Real-world Workload Dataset to Optimize LLM Serving Systems

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-16T11:27:17.378835Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c26e7288-8978-4be1-a3cf-b83a1a225c51 · outbound

This paper cites LoongServe: Efficiently Serving Long-Context Large Language Models with Elastic Sequence Parallelism.

SeaLLM: Service-Aware and Latency-Optimized Resource Sharing for Large Language Model Inference LoongServe: Efficiently Serving Long-Context Large Language Models with Elastic Sequence Parallelism

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-16T11:27:17.383632Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38ed9563-9588-4085-b534-e9e980d893e1 · outbound

This paper cites Fast Distributed Inference Serving for Large Language Models.

SeaLLM: Service-Aware and Latency-Optimized Resource Sharing for Large Language Model Inference Fast Distributed Inference Serving for Large Language Models

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-16T11:27:17.388272Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 635dc22d-7d7d-4672-964a-1ad137728cf6 · outbound

This paper cites dLoRA: Dynamically orches- trating requests and adapters for LoRA LLM serving.

SeaLLM: Service-Aware and Latency-Optimized Resource Sharing for Large Language Model Inference dLoRA: Dynamically orches- trating requests and adapters for LoRA LLM serving

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:27:17.907122Z

Source-reported events for the cited work

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

Observation 8fbf48e9-723a-482d-87ef-10e42c1b0b70 · outbound

This paper cites Antman: Dynamic scaling on gpu clusters for deep learning.

SeaLLM: Service-Aware and Latency-Optimized Resource Sharing for Large Language Model Inference Antman: Dynamic scaling on gpu clusters for deep learning

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:27:17.892653Z

Source-reported events for the cited work

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

Observation cf8516fd-f1f6-4a2b-bc5d-37625e1bc7ee · outbound

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

SeaLLM: Service-Aware and Latency-Optimized Resource Sharing for Large Language Model Inference Orca: A distributed serving system for Transformer-Based generative mod- els

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:27:17.878113Z

Source-reported events for the cited work

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

Observation 0f5f2a6b-ec18-4eee-ba3a-ac7b892d32a3 · outbound

This paper cites OPT: Open Pre-trained Transformer Language Models.

SeaLLM: Service-Aware and Latency-Optimized Resource Sharing for Large Language Model Inference OPT: Open Pre-trained Transformer Language Models

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-16T11:27:17.406179Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 316f5ec4-ee82-46ad-8360-c5da5ec6dd62 · outbound

This paper cites Multi- resource interleaving for deep learning training.

SeaLLM: Service-Aware and Latency-Optimized Resource Sharing for Large Language Model Inference Multi- resource interleaving for deep learning training

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:27:17.863787Z

Source-reported events for the cited work

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

Observation f1052953-1145-48e7-b62c-76bc95815f9f · outbound

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

SeaLLM: Service-Aware and Latency-Optimized Resource Sharing for Large Language Model Inference Dist- serve: Disaggregating prefill and decoding for goodput- optimized large language model serving

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T11:27:17.847784Z

Source-reported events for the cited work

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

Pith citing papers

Observation 592b20dd-ebed-4ee1-aa86-bea085db47fc · inbound

Scepsy: Serving Agentic Workflows Using Aggregate LLM Pipelines cites this paper.

Scepsy: Serving Agentic Workflows Using Aggregate LLM Pipelines SeaLLM: Service-Aware and Latency-Optimized Resource Sharing for Large Language Model Inference

Reference 62

Resolution: verified exact; arxiv_id, observed 2026-05-10T09:59:03.501623Z

Source-reported events for the cited work

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

Observation c5985ef2-03a5-4a08-9244-cc03e0a45768 · inbound

ROSE: Rollout On Serving GPUs via Cooperative Elasticity for Agentic RL cites this paper.

ROSE: Rollout On Serving GPUs via Cooperative Elasticity for Agentic RL SeaLLM: Service-Aware and Latency-Optimized Resource Sharing for Large Language Model Inference

Reference 93

Resolution: verified exact; arxiv_id, observed 2026-05-11T21:31:16.469748Z

Source-reported events for the cited work

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

Observation e5689416-4417-4ade-b42a-f2ea026da362 · inbound

ROSE: Rollout On Serving GPUs via Cooperative Elasticity for Agentic RL cites this paper.

ROSE: Rollout On Serving GPUs via Cooperative Elasticity for Agentic RL SeaLLM: Service-Aware and Latency-Optimized Resource Sharing for Large Language Model Inference

Reference 92

Resolution: verified exact; arxiv_id, observed 2026-05-21T08:39:53.275321Z

Source-reported events for the cited work

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