SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer | Paper Citation Record

Observation 5a1b21e5-e5f4-4521-aeb6-f6de3eb6b26f · outbound

This paper cites Phi-4-reasoning Technical Report.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer Phi-4-reasoning Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:12.065335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36e1e90f-7664-46b6-9f7b-327600ed9d06 · outbound

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

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer Gulavani, Alexey Tumanov, and Ramachandran Ramjee

Reference 2

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:12.156641Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92ea6a80-45d0-4643-a3d6-1f1627dbc47a · outbound

This paper cites Infiniband architecture specification volume 1 release 1.8.https://www.infini bandta.org/ibta-specification, Accessed: 2025.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer Infiniband architecture specification volume 1 release 1.8.https://www.infini bandta.org/ibta-specification, Accessed: 2025

Reference 3

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:12.216603Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1bd9d1a-57e5-47ab-a13b-5e2095273bfe · outbound

This paper cites LongBench: A bilingual, multitask benchmark for long context understanding.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer LongBench: A bilingual, multitask benchmark for long context understanding

Reference 4

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:12.259742Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90f88231-f561-42ce-b31d-034983fb7af3 · outbound

This paper cites TokenFlow: Responsive LLM text stream- ing serving under request burst via preemptive schedul- ing.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer TokenFlow: Responsive LLM text stream- ing serving under request burst via preemptive schedul- ing

Reference 5

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:12.360134Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation acceb86b-4b7c-4af9-9190-945eabe05800 · outbound

This paper cites Evaluating Large Language Models Trained on Code.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer Evaluating Large Language Models Trained on Code

Reference 6

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:12.479848Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20c871b3-a6b3-431d-bc2a-69a82736f6ea · outbound

This paper cites Retroinfer: A vector storage engine for scalable long-context LLM inference.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer Retroinfer: A vector storage engine for scalable long-context LLM inference

Reference 7

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:12.584938Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16178e22-2491-464b-88e5-19fd8f266fd0 · outbound

This paper cites Elastic GPU service instance families.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer Elastic GPU service instance families

Reference 8

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:12.721313Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18c0429d-1695-4288-acce-c52a2a710416 · outbound

This paper cites eRDMA.https://www.alibabacloud .com/help/en/ecs/user-guide/elastic-rdma-erdma, Accessed: 2025.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer eRDMA.https://www.alibabacloud .com/help/en/ecs/user-guide/elastic-rdma-erdma, Accessed: 2025

Reference 9

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:12.833863Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd7a11f3-3dd1-4e26-8a27-dbf2bf135df9 · outbound

This paper cites A2 ultra machine types.https://docs.c loud.google.com/compute/docs/accelerator-optimiz ed-machines#a2-ultra-vms, Accessed: 2025.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer A2 ultra machine types.https://docs.c loud.google.com/compute/docs/accelerator-optimiz ed-machines#a2-ultra-vms, Accessed: 2025

Reference 10

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:12.959928Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c50a4781-be92-40b3-a776-e8fc18801422 · outbound

This paper cites Computing instance.https://www.te ncentcloud.com/document/product/560/19701#GT4, Accessed: 2025.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer Computing instance.https://www.te ncentcloud.com/document/product/560/19701#GT4, Accessed: 2025

Reference 11

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:13.064781Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5257c786-1809-4850-8017-37a35a81bf17 · outbound

This paper cites NVIDIA dynamo platform.https: //developer.nvidia.com/dynamo, Accessed: 2025.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer NVIDIA dynamo platform.https: //developer.nvidia.com/dynamo, Accessed: 2025

Reference 12

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:13.135063Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9706a4c-a753-493a-aaba-c22ae4175ac1 · outbound

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

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer Fu, Stefano Ermon, Atri Rudra, and Christopher Ré

Reference 13

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:13.200993Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16a4b3a7-8577-4ef3-9b2a-abe8b57b95cf · outbound

This paper cites Deepseek-v3.2-exp: Boosting long- context efficiency with deepseek sparse attention.https: //github.com/deepseek-ai/DeepSeek-V3.2-Exp/blob/ main/DeepSeek_V3_2.pdf, Accessed: 2025.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer Deepseek-v3.2-exp: Boosting long- context efficiency with deepseek sparse attention.https: //github.com/deepseek-ai/DeepSeek-V3.2-Exp/blob/ main/DeepSeek_V3_2.pdf, Accessed: 2025

Reference 14

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:13.262681Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ef8f0b6-e997-48f8-89f3-4205d6870e1e · outbound

This paper cites DeepSeek-V3 Technical Report.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer DeepSeek-V3 Technical Report

Reference 15

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:13.321893Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab829f9a-1c01-4adf-9ac4-70e779731ecc · outbound

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

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer Pre- fillOnly: An inference engine for prefill-only workloads in large language model applications

Reference 16

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:13.361409Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8eeae7a4-03c7-47c3-9a1c-e632c27c51a4 · outbound

This paper cites The design and operation of CloudLab.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer The design and operation of CloudLab

Reference 17

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:13.412761Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f4ba4ca-34bf-4642-ae95-a4168b81eb4e · outbound

This paper cites Graham, Artem Y.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer Graham, Artem Y

Reference 18

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:13.463354Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68f34fcd-5a60-45f1-81f3-51f9404a14e6 · outbound

This paper cites Cost-efficient large language model serving for multi-turn conversations with CachedAtten- tion.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer Cost-efficient large language model serving for multi-turn conversations with CachedAtten- tion

Reference 19

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:13.530574Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bdfec739-9496-4adb-8558-49c9238dc7a1 · outbound

This paper cites Fast state restoration in LLM serving with HCache.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer Fast state restoration in LLM serving with HCache

Reference 20

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:13.606072Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91e69d8b-16b4-4014-adb1-f4fafcaa5a53 · outbound

This paper cites Weaver: Efficient multi-llm serving with attention offloading.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer Weaver: Efficient multi-llm serving with attention offloading

Reference 21

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:13.665888Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f8146844-e22f-4abb-8533-1663cabdc776 · outbound

This paper cites Hybrid multi- document summarization using pre-trained language models.Expert Syst.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer Hybrid multi- document summarization using pre-trained language models.Expert Syst

Reference 22

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:13.762133Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c050fe89-1eab-40a2-805b-e11282e526ba · outbound

This paper cites SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization

Reference 23

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:13.813892Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 219f1b3b-220d-4a35-92e8-f0d330fcdfa8 · outbound

This paper cites HATA: trainable and hardware-efficient hash-aware top-k at- tention for scalable large model inference.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer HATA: trainable and hardware-efficient hash-aware top-k at- tention for scalable large model inference

Reference 24

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:13.882652Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db2f6316-a3f1-415c-84ab-0a00d025d108 · outbound

This paper cites Olive: Accelerating large language models via hardware-friendly outlier-victim pair quantization.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer Olive: Accelerating large language models via hardware-friendly outlier-victim pair quantization

Reference 25

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:14.049340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec1bfb5d-b426-49a8-90d9-e39889c655cf · outbound

This paper cites an unresolved cited work.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer Unresolved cited work

Reference 26

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:14.163297Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 768defe2-4ffd-475a-85c2-35e87c35f7f0 · outbound

This paper cites OmniKV: Dynamic context selection for efficient long-context LLMs.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer OmniKV: Dynamic context selection for efficient long-context LLMs

Reference 27

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:14.336284Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e3109b47-3e74-44ff-8ce5-7f54b51ffd9e · outbound

This paper cites WaferLLM: Large language model inference at wafer scale.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer WaferLLM: Large language model inference at wafer scale

Reference 28

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:14.452112Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c1493b0-fd7f-4b3e-9cfd-d922e82bcefc · outbound

This paper cites Constructing A multi-hop QA dataset for comprehensive evaluation of reasoning steps.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer Constructing A multi-hop QA dataset for comprehensive evaluation of reasoning steps

Reference 29

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:14.600544Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a198e9ad-aeb4-4d46-9291-79305597b009 · outbound

This paper cites Mahoney, Yakun Sophia Shao, Kurt Keutzer, and Amir Gholami.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer Mahoney, Yakun Sophia Shao, Kurt Keutzer, and Amir Gholami

Reference 30

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:14.757015Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88f9298f-b660-4f3d-8b42-61c58cd035e9 · outbound

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

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer Inference without Interference: Disaggregate LLM Inference for Mixed Downstream Workloads

Reference 31

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:14.862617Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d39c685a-19f3-414b-8a27-6b841a53c3f4 · outbound

This paper cites Efficient attentions for long document summarization.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer Efficient attentions for long document summarization

Reference 32

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:14.985128Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b40def8a-c8e6-42a3-a7f2-cc4873d9822f · outbound

This paper cites Kamath, Ramya Prabhu, Jayashree Mohan, Si- mon Peter, Ramachandran Ramjee, and Ashish Panwar.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer Kamath, Ramya Prabhu, Jayashree Mohan, Si- mon Peter, Ramachandran Ramjee, and Ashish Panwar

Reference 33

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:15.132083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8fa02f65-eb89-4e6b-bea6-7c9341a4a8a8 · outbound

This paper cites Oaken: Fast and efficient LLM serving with online-offline hybrid KV cache quantization.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer Oaken: Fast and efficient LLM serving with online-offline hybrid KV cache quantization

Reference 34

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:15.245943Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7ba4d0b-9423-4b9d-913c-c231645e266c · outbound

This paper cites Aqua: Network-accelerated memory offloading for llms in scale-up GPU domains.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer Aqua: Network-accelerated memory offloading for llms in scale-up GPU domains

Reference 35

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:15.349109Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24cbc52d-330e-4989-9f4a-90e53d334753 · outbound

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

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer Efficient memory management for large language model serving with PagedAttention

Reference 36

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:15.510728Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17372a46-8264-4d95-afef-b95fe357b59f · outbound

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

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer InfiniGen: Efficient generative inference of large language models with dynamic KV cache management

Reference 37

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:15.620746Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 480830a5-bd9f-437d-af28-cd77bd7bdc71 · outbound

This paper cites ClusterKV: Manipulating LLM KV cache in semantic space for recallable compression.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer ClusterKV: Manipulating LLM KV cache in semantic space for recallable compression

Reference 38

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:15.687846Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9168d745-635f-4f6e-8fa4-8e125894b1df · outbound

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

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer Cachegen: KV cache compression and streaming for fast large language model serving

Reference 39

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:15.781253Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d4893e6-b746-483c-bb52-f4cf6674b763 · outbound

This paper cites Helix: Serving large language models over heterogeneous GPUs and network via max-flow.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer Helix: Serving large language models over heterogeneous GPUs and network via max-flow

Reference 40

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:15.839066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a679fda-2331-4e5e-9665-2264f296e165 · outbound

This paper cites an unresolved cited work.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer Unresolved cited work

Reference 41

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:15.924508Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d78d0d49-af54-4119-9d9a-f3f00887bd17 · outbound

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

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer Heterogeneity-aware cluster scheduling policies for deep learning workloads

Reference 42

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:16.042849Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71bf4129-a72d-4573-bac6-9efb850ce811 · outbound

This paper cites GPT-5 is here.https://openai.com/gpt-5, Accessed: 2025.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer GPT-5 is here.https://openai.com/gpt-5, Accessed: 2025

Reference 43

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:16.128417Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b7f1b082-5cf6-48bb-9c06-8d658b5b644d · outbound

This paper cites InstAttention: In-storage attention offloading for cost-effective long-context LLM inference.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer InstAttention: In-storage attention offloading for cost-effective long-context LLM inference

Reference 44

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:16.241941Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation abe3057a-892d-4051-bb43-c6f60a269d71 · outbound

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

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer Splitwise: Efficient generative LLM inference using phase splitting

Reference 45

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:16.318560Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27130887-cb0f-40a2-b12a-76381da4c0e3 · outbound

This paper cites vAttention: Dynamic memory management for serving llms with- out PagedAttention.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer vAttention: Dynamic memory management for serving llms with- out PagedAttention

Reference 46

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:16.451886Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5e26cee-d669-45e7-882f-c3eb61e3177f · outbound

This paper cites Mooncake: Trading more storage for less computation - A kvcache-centric architecture for serving LLM chatbot.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer Mooncake: Trading more storage for less computation - A kvcache-centric architecture for serving LLM chatbot

Reference 47

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:16.537189Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d6ea45bf-cee7-42e9-9983-df5588d67c2d · outbound

This paper cites Breakfast of champions: to- wards zero-copy serialization with NIC scatter-gather.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer Breakfast of champions: to- wards zero-copy serialization with NIC scatter-gather

Reference 48

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:16.641220Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d950655-6fe7-4926-aac1-f3e6f96b0c3f · outbound

This paper cites Code Llama: Open Foundation Models for Code.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer Code Llama: Open Foundation Models for Code

Reference 49

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:16.739282Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 447a7dc3-5d2d-423e-bdfa-5ff0092eab9e · outbound

This paper cites Partner success with AWS.http s://aws.amazon.com/partners/success, Accessed: 2025.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer Partner success with AWS.http s://aws.amazon.com/partners/success, Accessed: 2025

Reference 50

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:16.813479Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee8d85d9-7e40-4039-838e-17fa95eaebbb · outbound

This paper cites Recommended GPU instances.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer Recommended GPU instances

Reference 51

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:16.899455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c047fda4-07cc-4f71-b038-ff25ef0f7af2 · outbound

This paper cites Gonzalez, and Ion Stoica.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer Gonzalez, and Ion Stoica

Reference 52

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:16.985377Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9af42044-f506-4a87-9fec-2e54abad43cf · outbound

This paper cites FlexGen: High-throughput generative inference of large language models with a single GPU.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer FlexGen: High-throughput generative inference of large language models with a single GPU

Reference 53

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:17.076373Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 707ee9f0-01b3-45d7-a105-d5db55c090ac · outbound

This paper cites Maguire Jr., and Dejan Kostic.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer Maguire Jr., and Dejan Kostic

Reference 54

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:17.144547Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dbc46c3f-e186-4485-85f6-8d25c5de5894 · outbound

This paper cites an unresolved cited work.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer Unresolved cited work

Reference 55

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:17.265620Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89ed69c4-7aa6-4a59-bc1c-b0c462225e9b · outbound

This paper cites PowerInfer: Fast large language model serving with a consumer-grade GPU.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer PowerInfer: Fast large language model serving with a consumer-grade GPU

Reference 56

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:17.444363Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51f82ed7-c4e8-4c3d-b5f3-aeb6c480360b · outbound

This paper cites Preble: Efficient distributed prompt scheduling for LLM serving.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer Preble: Efficient distributed prompt scheduling for LLM serving

Reference 57

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:17.514460Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d28ecb4-9dd4-4959-a4b1-fb00d6b26d62 · outbound

This paper cites Déjàvu: Kv-cache stream- ing for fast, fault-tolerant generative LLM serving.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer Déjàvu: Kv-cache stream- ing for fast, fault-tolerant generative LLM serving

Reference 58

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:17.609483Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 53cef9d2-a140-470a-a865-0969cd1daecd · outbound

This paper cites QUEST: query-aware sparsity for efficient long-context LLM inference.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer QUEST: query-aware sparsity for efficient long-context LLM inference

Reference 59

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:17.673473Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89b885dc-3922-4b61-ba37-07abbaaa4c40 · outbound

This paper cites Gemma 3 Technical Report.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer Gemma 3 Technical Report

Reference 60

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:17.746835Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0ec2726-551d-4284-97bd-3eac364d487d · outbound

This paper cites The Llama 3 Herd of Models.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer The Llama 3 Herd of Models

Reference 61

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:17.878772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 690116a3-8c48-4e8c-a601-00df14918396 · outbound

This paper cites Qwen3 Technical Report.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer Qwen3 Technical Report

Reference 62

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:17.977097Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b44aee88-2c5d-4a16-9047-addd2b89c0bd · outbound

This paper cites Gomez, Lukasz Kaiser, and Illia Polosukhin.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer Gomez, Lukasz Kaiser, and Illia Polosukhin

Reference 63

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:18.061323Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 07710b8f-929d-4d72-b195-898d83b6990d · outbound

This paper cites KVCache cache in the wild: Characterizing and optimizing KVCache cache at a large cloud provider, 2025.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer KVCache cache in the wild: Characterizing and optimizing KVCache cache at a large cloud provider, 2025

Reference 64

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:18.149540Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20d9eb3b-868a-40b7-b2fa-190b65c8cbee · outbound

This paper cites From prefix cache to fusion RAG cache: Accelerating LLM inference in retrieval-augmented generation.CoRR, abs/2601.12904, 2026.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer From prefix cache to fusion RAG cache: Accelerating LLM inference in retrieval-augmented generation.CoRR, abs/2601.12904, 2026

Reference 65

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:18.205939Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24c399bc-9622-4b97-9ed9-f5c1554eaaa7 · outbound

This paper cites Element-aware summarization with large language models: Expert-aligned evaluation and chain-of- thought method.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer Element-aware summarization with large language models: Expert-aligned evaluation and chain-of- thought method

Reference 66

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:18.286738Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30eca377-2f8e-4662-b1aa-9842445cd7ed · outbound

This paper cites Phoenixos: Concurrent os-level GPU checkpoint and restore with validated speculation.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer Phoenixos: Concurrent os-level GPU checkpoint and restore with validated speculation

Reference 67

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:18.371796Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation faa59009-37cc-4db8-96e1-f6165a693b8d · outbound

This paper cites LoongServe: Efficiently serv- ing long-context large language models with elastic se- quence parallelism.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer LoongServe: Efficiently serv- ing long-context large language models with elastic se- quence parallelism

Reference 68

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:18.481672Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation afb05c1d-4a7a-4e15-88a7-17e8ff8fff54 · outbound

This paper cites DuoAttention: Efficient long-context LLM inference with retrieval and streaming heads.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer DuoAttention: Efficient long-context LLM inference with retrieval and streaming heads

Reference 69

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:18.554551Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a29c98f4-00f5-4917-b2c9-7d948f907eca · outbound

This paper cites Efficient streaming language models with attention sinks.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer Efficient streaming language models with attention sinks

Reference 70

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:18.644504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6dbbf075-439e-47e9-bfd3-d104192ffc0d · outbound

This paper cites CacheBlend: Fast large language model serving for RAG with cached knowledge fusion.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer CacheBlend: Fast large language model serving for RAG with cached knowledge fusion

Reference 71

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:18.715514Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f05b22b4-7696-4abe-826e-4e0913b26c81 · outbound

This paper cites FlashInfer: Efficient and customizable attention engine for LLM inference serving.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer FlashInfer: Efficient and customizable attention engine for LLM inference serving

Reference 72

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:18.842799Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e64eb608-11df-4107-9838-aa70d32b32af · outbound

This paper cites Willcock, Suvinay Sub- ramanian, Felix Chern, Alek Andreev, Shreya Pathak, Felix X.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer Willcock, Suvinay Sub- ramanian, Felix Chern, Alek Andreev, Shreya Pathak, Felix X

Reference 73

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:18.946243Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d251480-4d71-4901-8605-8624723641b2 · outbound

This paper cites Orca: A distributed 17 serving system for transformer-based generative mod- els.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer Orca: A distributed 17 serving system for transformer-based generative mod- els

Reference 74

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:19.040565Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 555c11d3-bd72-4d90-bf87-6e816a092f19 · outbound

This paper cites Stateful large language model serving with Pensieve.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer Stateful large language model serving with Pensieve

Reference 75

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:19.124125Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1192aa68-5c5d-4b93-8287-a82c84c26301 · outbound

This paper cites an unresolved cited work.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer Unresolved cited work

Reference 76

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:19.211420Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 402fccba-1f55-4d3d-b334-3a0acd67166a · outbound

This paper cites Na- tive sparse attention: Hardware-aligned and natively trainable sparse attention.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer Na- tive sparse attention: Hardware-aligned and natively trainable sparse attention

Reference 77

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:19.286688Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c82d628-7573-425e-8245-af6f02bfb635 · outbound

This paper cites Rethinking database high availability with RDMA networks.Proc.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer Rethinking database high availability with RDMA networks.Proc

Reference 78

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:19.375120Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 377907d7-b3b5-4727-91b4-89842814a8f0 · outbound

This paper cites GPU checkpoint/restore made fast and lightweight.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer GPU checkpoint/restore made fast and lightweight

Reference 79

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:19.465535Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4208fbf-b923-4b7d-8b31-2468997733fb · outbound

This paper cites Jenga: Effective memory manage- ment for serving LLM with heterogeneity.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer Jenga: Effective memory manage- ment for serving LLM with heterogeneity

Reference 80

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:19.526988Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d81aa742-8004-4f47-8637-cb295962f17c · outbound

This paper cites BlitzScale: Fast and live large model autoscaling with O(1) host caching.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer BlitzScale: Fast and live large model autoscaling with O(1) host caching

Reference 81

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:19.589085Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 492e4f93-fd0e-4e3b-9c76-b72f1f4028fc · outbound

This paper cites HACK: homomorphic acceleration via compression of the key- value cache for disaggregated LLM inference.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer HACK: homomorphic acceleration via compression of the key- value cache for disaggregated LLM inference

Reference 82

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:19.661302Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa1106db-6561-4d4d-9c62-25479bce809b · outbound

This paper cites Barrett, Zhangyang Wang, and Beidi Chen.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer Barrett, Zhangyang Wang, and Beidi Chen

Reference 83

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:19.735381Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54039205-e481-42a2-873b-a180b6ef5095 · outbound

This paper cites Gonzalez, Clark W.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer Gonzalez, Clark W

Reference 84

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:19.788776Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d86c767e-91d2-438f-83f9-fb8f8c5dcbe5 · outbound

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

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer Dist- Serve: Disaggregating prefill and decoding for goodput- optimized large language model serving

Reference 85

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:19.869913Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d5dbca3c-7b69-4390-b99b-ed9965171a49 · outbound

This paper cites NanoFlow: Towards optimal large language model serving throughput.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer NanoFlow: Towards optimal large language model serving throughput

Reference 86

Resolution: unresolved; no resolver link, observed 2026-07-31T16:21:19.946822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6bb2120-4bfe-4d09-ab2a-7f7d53b1ff4e · outbound

This paper cites an unresolved cited work.

SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer Unresolved cited work

Reference 964

Resolution: parse uncertain; no resolver link, observed 2026-07-31T16:21:17.363791Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers