Paper Citation Record · LEDGER

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU

As of 8 August 2026, this Paper Citation Record lists 75 of 75 outbound references and 2 inbound Pith citation observations for arXiv:2506.20187.

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

pith.paper-citation-record.v1
2506.20187 v2

Coverage vector

measured 75 of 75 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T23:00:11.244159Z

measured 77 of 77 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-26T12:19:30.666750Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-04T07:59:40.383102Z

Reference resolution

75 of 75 outbound references displayed

verified exact2
verified fuzzy4
unresolved69
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 785965b3-dc4b-4588-8dce-98c0739f74e5 · outbound

This paper cites an unresolved cited work.

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU Unresolved cited work

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T23:00:11.017359Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 28d100c7-787c-4b44-bede-46058dc61525 · outbound

This paper cites an unresolved cited work.

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU Unresolved cited work

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T23:00:11.022454Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 759f16c2-a05f-49db-9a28-ccc79cc1085a · outbound

This paper cites an unresolved cited work.

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU Unresolved cited work

Reference 3

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:00:11.868015Z

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 9a1f3507-329b-44eb-827a-7a34d901c4ec · outbound

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

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-06T23:00:11.029267Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 39ae85f0-c3b5-43bc-8a4b-9c7c319167af · outbound

This paper cites Longformer: The Long-Document Transformer.

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU Longformer: The Long-Document Transformer

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-06T23:00:11.032835Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c5c6c8e9-800c-4fdb-8526-263cb501b268 · outbound

This paper cites an unresolved cited work.

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU Unresolved cited work

Reference 6

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:00:11.860102Z

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 21d94218-256a-4189-b9d6-3a072d6ad3fb · outbound

This paper cites an unresolved cited work.

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU Unresolved cited work

Reference 7

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:00:11.851918Z

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 6946337e-e57d-4c3c-bb57-22d04d94e796 · outbound

This paper cites 2025.{IMPRESS}: An{Importance-Informed}{ Multi-Tier} Prefix{KV} Storage System for Large Language Model Inference.

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU 2025.{IMPRESS}: An{Importance-Informed}{ Multi-Tier} Prefix{KV} Storage System for Large Language Model Inference

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:00:11.843573Z

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 cb5520d9-0532-4caf-b113-ca8020818d57 · outbound

This paper cites an unresolved cited work.

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU Unresolved cited work

Reference 9

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:00:11.835196Z

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 012ce635-c357-4104-93e3-4e26f34ee054 · outbound

This paper cites Few-Shot NLG with Pre-Trained Language Model.

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU Few-Shot NLG with Pre-Trained Language Model

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-08-06T23:00:11.445981Z

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 4da509f6-c852-4b23-b3d7-e6f984c1299c · outbound

This paper cites an unresolved cited work.

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU Unresolved cited work

Reference 11

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:00:11.827610Z

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 e2eaa2bf-1941-4352-a955-806e65df6812 · outbound

This paper cites an unresolved cited work.

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU Unresolved cited work

Reference 12

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:00:11.818847Z

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 be8746f0-4cde-48fa-9daf-beb43fc3ad8e · outbound

This paper cites an unresolved cited work.

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU Unresolved cited work

Reference 13

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:00:11.810467Z

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 c46bbd5c-cefe-4d6a-8257-a9bd255f5e10 · outbound

This paper cites an unresolved cited work.

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU Unresolved cited work

Reference 14

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:00:11.802212Z

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 c79b3b0b-5e97-454e-8fc3-9898097c5917 · outbound

This paper cites QAQ: Quality Adaptive Quantization for LLM KV Cache.

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU QAQ: Quality Adaptive Quantization for LLM KV Cache

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T23:00:11.062539Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d6dab555-365b-475e-852b-42b9835b1450 · outbound

This paper cites an unresolved cited work.

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU Unresolved cited work

Reference 16

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:00:11.794836Z

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 402982f5-ca92-4ca9-8baf-b8a47501813b · outbound

This paper cites 2024.{Cost- Efficient} large language model serving for multi-turn conversations with{CachedAttention}.

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU 2024.{Cost- Efficient} large language model serving for multi-turn conversations with{CachedAttention}

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-06T23:00:11.067881Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f11429a-5466-4508-bee2-6551d62fd90f · outbound

This paper cites an unresolved cited work.

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU Unresolved cited work

Reference 18

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:00:11.782156Z

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 cee4d1dc-3dc9-4739-a12f-2b3bae0e6038 · outbound

This paper cites an unresolved cited work.

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU Unresolved cited work

Reference 19

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:00:11.772235Z

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 19c85dd1-eaf2-46ec-b9ce-a79b014b1e82 · outbound

This paper cites KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization.

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-06T23:00:11.077208Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f11acfcb-6238-4764-985a-46fef35084c6 · outbound

This paper cites EdgeLLM: A Highly Efficient CPU-FPGA Heterogeneous Edge Accelerator for Large Language Models.

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU EdgeLLM: A Highly Efficient CPU-FPGA Heterogeneous Edge Accelerator for Large Language Models

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-08-06T23:00:11.422577Z

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 6cbc9942-3086-4cae-92f5-e6ef33476007 · outbound

This paper cites Locret: Enhancing Eviction in Long-Context LLM Inference with Trained Retaining Heads on Consumer-Grade Devices.

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU Locret: Enhancing Eviction in Long-Context LLM Inference with Trained Retaining Heads on Consumer-Grade Devices

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-06T23:00:11.083856Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f61da3c-dced-46d2-ab09-1ef6ec0816e3 · outbound

This paper cites an unresolved cited work.

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU Unresolved cited work

Reference 23

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:00:11.763557Z

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 617bf4fd-73a8-4d10-b005-370ebe5154a1 · outbound

This paper cites an unresolved cited work.

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU Unresolved cited work

Reference 24

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:00:11.754860Z

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 6acb8aa0-8d0e-42d9-9f0f-43b53db11b11 · outbound

This paper cites Hydragen: High-Throughput LLM Inference with Shared Prefixes.

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU Hydragen: High-Throughput LLM Inference with Shared Prefixes

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-06T23:00:11.093224Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21afadde-ff39-4134-b0a2-f1cfc01bb7a9 · outbound

This paper cites an unresolved cited work.

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU Unresolved cited work

Reference 26

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:00:11.746822Z

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 d9a93331-e1fa-4f97-8275-cbc1e0ac6b15 · outbound

This paper cites an unresolved cited work.

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU Unresolved cited work

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-06T23:00:11.099764Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 912b82a9-3319-4208-8a7c-0d482be9dc51 · outbound

This paper cites an unresolved cited work.

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU Unresolved cited work

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-06T23:00:11.105890Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee8dd3b8-450d-4674-b743-ccd47dfcf2fb · outbound

This paper cites an unresolved cited work.

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU Unresolved cited work

Reference 29

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:00:11.726465Z

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 4080c216-4d57-4d76-9ba9-892bd659b4c9 · outbound

This paper cites an unresolved cited work.

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU Unresolved cited work

Reference 30

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:00:11.718521Z

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 26fc1fb9-71ea-4b22-9736-91ecefa87d01 · outbound

This paper cites Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security.

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-06T23:00:11.114538Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 105f50a3-4f92-4c81-8eca-511cfca885aa · outbound

This paper cites an unresolved cited work.

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU Unresolved cited work

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-06T23:00:11.118383Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ef143eb-2b8a-420b-8be2-f182a9b87772 · outbound

This paper cites Infinite-LLM: Efficient LLM Service for Long Context with DistAttention and Distributed KVCache.

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU Infinite-LLM: Efficient LLM Service for Long Context with DistAttention and Distributed KVCache

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-06T23:00:11.123886Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 86954114-e5c2-44e4-8d49-51936a7771fd · outbound

This paper cites an unresolved cited work.

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU Unresolved cited work

Reference 34

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:00:11.697394Z

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 0a5912b1-1dd2-4377-8575-01d21cf51f36 · outbound

This paper cites an unresolved cited work.

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU Unresolved cited work

Reference 35

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:00:11.690719Z

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 fa711cf2-30be-4290-a2fd-079d1eb317dc · outbound

This paper cites an unresolved cited work.

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU Unresolved cited work

Reference 36

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:00:11.681268Z

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 b5bf4945-8f0c-4d60-b4c3-5adf40afa034 · outbound

This paper cites RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval.

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-06T23:00:11.130073Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2499fee-d581-4119-a2e6-a6c6076a0065 · outbound

This paper cites an unresolved cited work.

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU Unresolved cited work

Reference 38

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:00:11.664379Z

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 3b933033-63d9-44ac-aff3-402f563405c4 · outbound

This paper cites MMLongBench-Doc: Benchmarking Long-context Document Understanding with Visualizations.

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU MMLongBench-Doc: Benchmarking Long-context Document Understanding with Visualizations

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-06T23:00:11.143406Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 402f0165-0bc0-4327-bfe7-3940521b907e · outbound

This paper cites an unresolved cited work.

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU Unresolved cited work

Reference 40

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:00:11.672992Z

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 235fa288-fd17-4603-8bad-20c4e5932282 · outbound

This paper cites an unresolved cited work.

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU Unresolved cited work

Reference 41

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:00:11.648774Z

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 ce740891-810a-48c2-b92e-2e3cb7a9f7f1 · outbound

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

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU InstInfer: In-Storage Attention Offloading for Cost-Effective Long-Context LLM Inference

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-06T23:00:11.154210Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e025d8e9-ec6e-4e38-9d16-6a5fc8663390 · outbound

This paper cites an unresolved cited work.

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU Unresolved cited work

Reference 43

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:00:11.656292Z

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 5b5abeb3-511f-47bf-bc57-519d82b1a3aa · outbound

This paper cites an unresolved cited work.

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU Unresolved cited work

Reference 44

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:00:11.632833Z

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 e06dcd07-280d-4555-be4b-36911bd2f7ce · outbound

This paper cites Compressive Transformers for Long-Range Sequence Modelling.

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU Compressive Transformers for Long-Range Sequence Modelling

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-06T23:00:11.164618Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e523da6-4464-4cda-97c4-2b1a80e42139 · outbound

This paper cites an unresolved cited work.

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU Unresolved cited work

Reference 46

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:00:11.640451Z

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 5568e98f-9628-4a2d-b939-7a04aeaab1fb · outbound

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

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU PowerInfer: Fast Large Language Model Serving with a Consumer-grade GPU

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-06T23:00:11.173785Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 245b5dd0-586a-42fa-aa7c-77aecf5a2c76 · outbound

This paper cites AlignedKV: Reducing Memory Access of KV-Cache with Precision-Aligned Quantization.

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU AlignedKV: Reducing Memory Access of KV-Cache with Precision-Aligned Quantization

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-06T23:00:11.177146Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a750796-1dc1-41eb-a62b-34ac31a4d186 · outbound

This paper cites an unresolved cited work.

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU Unresolved cited work

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-06T23:00:11.167977Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f880a37-c0fb-4cc4-acf9-7b9a71498846 · outbound

This paper cites In International Conference on Machine Learning.

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU In International Conference on Machine Learning

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:00:11.621323Z

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 a0c58dda-5e75-4ea5-af08-6f33bfd1d740 · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU LLaMA: Open and Efficient Foundation Language Models

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-06T23:00:11.184844Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6e50baf-9074-43ee-98da-7b86ead4a4cc · outbound

This paper cites an unresolved cited work.

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU Unresolved cited work

Reference 52

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:00:11.593081Z

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 769d6449-d2c3-4c96-a6cd-1a7aa80c593b · outbound

This paper cites an unresolved cited work.

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU Unresolved cited work

Reference 53

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:00:11.610996Z

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 a2d4e614-e073-4746-9d83-23aa22c60377 · outbound

This paper cites an unresolved cited work.

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU Unresolved cited work

Reference 54

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:00:11.602869Z

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 00cbb8b3-40f4-4047-bc69-5ab3014aa410 · outbound

This paper cites an unresolved cited work.

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU Unresolved cited work

Reference 55

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:00:11.585902Z

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 9faa91c4-4c95-43d9-ab22-8e75d17d0ddf · outbound

This paper cites HuggingFace's Transformers: State-of-the-art Natural Language Processing.

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU HuggingFace's Transformers: State-of-the-art Natural Language Processing

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-06T23:00:11.201904Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc9c0f6d-fb3a-42bc-9121-98fa8597dadb · outbound

This paper cites Attention Is All You Need.

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU Attention Is All You Need

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-06T23:00:11.190412Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b265b223-eb3a-43b3-b1eb-2b0e57b0a087 · outbound

This paper cites LOOK-M: Look-Once Optimization in KV Cache for Efficient Multimodal Long-Context Inference.

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU LOOK-M: Look-Once Optimization in KV Cache for Efficient Multimodal Long-Context Inference

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-06T23:00:11.193142Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 72268e6b-f74b-4d8c-bf88-5a2f34360f62 · outbound

This paper cites PyramidInfer: Pyramid KV Cache Compression for High-throughput LLM Inference.

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU PyramidInfer: Pyramid KV Cache Compression for High-throughput LLM Inference

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-06T23:00:11.211770Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a237ed3-4f35-4776-8544-477683237d4a · outbound

This paper cites CoRR (2024).

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU CoRR (2024)

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:00:11.577027Z

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 53660d0d-4639-4fd1-8374-2cc1c21b9dff · outbound

This paper cites an unresolved cited work.

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU Unresolved cited work

Reference 61

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:00:11.568169Z

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 8b265304-d579-481a-a31f-dab3b8fadf1e · outbound

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

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU LoongServe: Efficiently Serving Long-Context Large Language Models with Elastic Sequence Parallelism

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-06T23:00:11.204437Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef238234-d80b-46c7-922d-49b515f2b452 · outbound

This paper cites ThinK: Thinner Key Cache by Query-Driven Pruning.

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU ThinK: Thinner Key Cache by Query-Driven Pruning

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-06T23:00:11.208166Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6105dbbd-527b-4de3-ac63-e16d37d08ba3 · outbound

This paper cites an unresolved cited work.

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU Unresolved cited work

Reference 64

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:00:11.546105Z

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 982655e1-4327-4add-b550-c68d1e0d768d · outbound

This paper cites CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusion.

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusion

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-06T23:00:11.214547Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d4f426f-5312-485f-ae9a-e17e6d90758b · outbound

This paper cites A Survey of Large Language Models.

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU A Survey of Large Language Models

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-06T23:00:11.232057Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f441ba8-0dff-49a9-a7c4-17d4fbf2545c · outbound

This paper cites PQCache: Product Quantization-based KVCache for Long Context LLM Inference.

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU PQCache: Product Quantization-based KVCache for Long Context LLM Inference

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-06T23:00:11.220828Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21dcce89-2d65-49be-8219-088415133011 · outbound

This paper cites an unresolved cited work.

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU Unresolved cited work

Reference 68

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:00:11.558370Z

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 786f3f45-932e-4111-858c-a3bb056ef05c · outbound

This paper cites A Survey on Efficient Inference for Large Language Models.

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU A Survey on Efficient Inference for Large Language Models

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-06T23:00:11.240664Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 86c39ce3-400f-4d9b-aaf4-52551a49c237 · outbound

This paper cites an unresolved cited work.

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU Unresolved cited work

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-06T23:00:11.229346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd39bc2f-a8a1-4b66-ac9e-69c0233636d2 · outbound

This paper cites ALISA: Accelerating Large Language Model Inference via Sparsity-Aware KV Caching.

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU ALISA: Accelerating Large Language Model Inference via Sparsity-Aware KV Caching

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-06T23:00:11.235417Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e078f43c-07b0-446d-9db3-d63d4217b598 · outbound

This paper cites an unresolved cited work.

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU Unresolved cited work

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-06T23:00:11.238133Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e48076b-dbe4-4a8a-82fc-b0250b397dc8 · outbound

This paper cites SampleAttention: Near-Lossless Acceleration of Long Context LLM Inference with Adaptive Structured Sparse Attention.

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU SampleAttention: Near-Lossless Acceleration of Long Context LLM Inference with Adaptive Structured Sparse Attention

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-06T23:00:11.244159Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fdbb2d96-e0a5-4a4d-b3b4-ad2d91310eed · outbound

This paper cites InProceedings of the 29th Symposium on Operating Systems Principles.

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU InProceedings of the 29th Symposium on Operating Systems Principles

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-06T23:00:11.103318Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3479ea6b-be0f-4aa1-bf07-2c93a4a24d47 · outbound

This paper cites In Proceedings of the ACM SIGCOMM 2024 Conference.

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU In Proceedings of the ACM SIGCOMM 2024 Conference

Reference 2024

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:00:11.706064Z

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.

Pith citing papers

Observation 9933c708-0a8d-4273-8971-2369de29cb48 · inbound

Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference cites this paper.

Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU

Reference 24

Resolution: verified exact; arxiv_id, observed 2026-05-17T11:16:32.022030Z

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 85e550da-29fd-484b-a18a-8015daf27092 · inbound

Agent-Assisted Side-Channel Attacks on Non-Prefix KV Cache in RAG cites this paper.

Agent-Assisted Side-Channel Attacks on Non-Prefix KV Cache in RAG Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-07-04T07:59:40.384450Z

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.