GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM | Paper Citation Record

Observation 4c274a29-48b0-4191-a303-036c206199ef · inbound

SGLang: Efficient Execution of Structured Language Model Programs cites this paper.

SGLang: Efficient Execution of Structured Language Model Programs GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-05-12T08:20:01.181115Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 1c1458c6-6319-4acf-bd58-3c52b8d758d3 · inbound

Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey cites this paper.

Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

Reference 183

Resolution: verified exact; arxiv_id, observed 2026-05-13T11:32:36.921300Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 787d8d4b-0a63-4247-99d0-0fe6d7293239 · inbound

Multi-Bin Batching for Increasing LLM Inference Throughput cites this paper.

Multi-Bin Batching for Increasing LLM Inference Throughput GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-11T23:56:23.192461Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 01665fc2-6ef2-4415-bf6a-6d14cac1887e · inbound

XKV: Personalized KV Cache Memory Reduction for Long-Context LLM Inference cites this paper.

XKV: Personalized KV Cache Memory Reduction for Long-Context LLM Inference GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-11T20:18:17.868031Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4bfc02b8-2457-4587-bdeb-4c0b0f90e1c1 · inbound

Low-Rank Correction for Quantized LLMs cites this paper.

Low-Rank Correction for Quantized LLMs GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-11T18:35:26.804829Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44398d71-fd32-41e3-987c-c6fb764c9fef · inbound

Lexico: Extreme KV Cache Compression via Sparse Coding over Universal Dictionaries cites this paper.

Lexico: Extreme KV Cache Compression via Sparse Coding over Universal Dictionaries GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-11T17:32:39.949962Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6f96a3d-b421-445a-84a6-69172711e76a · inbound

CSR:Achieving 1 Bit Key-Value Cache via Sparse Representation cites this paper.

CSR:Achieving 1 Bit Key-Value Cache via Sparse Representation GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-11T14:43:53.743169Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae71be05-5aad-457e-b094-8edc2005b616 · inbound

More Tokens, Lower Precision: Towards the Optimal Token-Precision Trade-off in KV Cache Compression cites this paper.

More Tokens, Lower Precision: Towards the Optimal Token-Precision Trade-off in KV Cache Compression GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-11T13:52:48.712247Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a50b5f7-d468-4e8b-bfbc-e2ed5fb7edd7 · inbound

ResQ: Mixed-Precision Quantization of Large Language Models with Low-Rank Residuals cites this paper.

ResQ: Mixed-Precision Quantization of Large Language Models with Low-Rank Residuals GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-11T12:22:38.849655Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8108889f-c38f-4a3f-b0bb-daabff8c9a4b · inbound

DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs cites this paper.

DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-11T11:57:17.934982Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 564100b0-98ef-440b-bb33-3416f19c907b · inbound

A Survey on Large Language Model Acceleration based on KV Cache Management cites this paper.

A Survey on Large Language Model Acceleration based on KV Cache Management GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

Reference 92

Resolution: unresolved; no resolver link, observed 2026-08-11T00:38:47.324395Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2377e117-9098-4867-96d4-78956e29de2a · inbound

Efficiently Serving Large Multimodal Models Using EPD Disaggregation cites this paper.

Efficiently Serving Large Multimodal Models Using EPD Disaggregation GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-11T04:29:34.728199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d80ec495-591c-4b2b-98d8-d3be9eca364f · inbound

Cache Me If You Must: Adaptive Key-Value Quantization for Large Language Models cites this paper.

Cache Me If You Must: Adaptive Key-Value Quantization for Large Language Models GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-09T20:34:01.250786Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1c3a8f3-05a1-48fe-98ae-f71f82e1b2af · inbound

PolarQuant: Leveraging Polar Transformation for Efficient Key Cache Quantization and Decoding Acceleration cites this paper.

PolarQuant: Leveraging Polar Transformation for Efficient Key Cache Quantization and Decoding Acceleration GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-09T18:46:51.073129Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6284fb8-9ee7-4f61-9079-8df0022ccc90 · inbound

PolarQuant: Quantizing KV Caches with Polar Transformation cites this paper.

PolarQuant: Quantizing KV Caches with Polar Transformation GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-09T13:26:55.388294Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a312f7a9-8693-4c31-a9e8-20d62d99656f · inbound

HACK: Homomorphic Acceleration via Compression of the Key-Value Cache for Disaggregated LLM Inference cites this paper.

HACK: Homomorphic Acceleration via Compression of the Key-Value Cache for Disaggregated LLM Inference GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-09T04:32:01.224806Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0872bdf5-f05e-4ce2-b24d-f984a37244e5 · inbound

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters cites this paper.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.538291Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d3def96-2c07-4025-8407-26f66ab15109 · inbound

Inference-time sparse attention with asymmetric indexing cites this paper.

Inference-time sparse attention with asymmetric indexing GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-08T05:56:55.130242Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d31dcdd4-0ac6-4064-8f01-5ef9ccc71d1c · inbound

QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache cites this paper.

QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-09T04:28:03.935822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ccfd40f-ed8b-4b96-b152-e504110dea8f · inbound

LogQuant: Log-Distributed 2-Bit Quantization of KV Cache with Superior Accuracy Preservation cites this paper.

LogQuant: Log-Distributed 2-Bit Quantization of KV Cache with Superior Accuracy Preservation GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-22T22:12:11.639029Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 85e7572d-1ce2-4964-828f-7d62707c5a7a · inbound

TurboQuant: Online Vector Quantization with Near-optimal Distortion Rate cites this paper.

TurboQuant: Online Vector Quantization with Near-optimal Distortion Rate GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

Reference 33

Resolution: verified exact; arxiv_id, observed 2026-05-20T08:09:22.423835Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 314a7d1b-a983-4a50-a744-b0f41a356f60 · inbound

Accurate KV Cache Quantization with Outlier Tokens Tracing cites this paper.

Accurate KV Cache Quantization with Outlier Tokens Tracing GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:38.937281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 704c6af7-e828-4af3-a14c-e0b581fc656f · inbound

Win Fast or Lose Slow: Balancing Speed and Accuracy in Latency-Sensitive Decisions of LLMs cites this paper.

Win Fast or Lose Slow: Balancing Speed and Accuracy in Latency-Sensitive Decisions of LLMs GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:45.550536Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e68ccd2-51c8-47b1-a411-fa6b04f267a7 · inbound

TailorKV: A Hybrid Framework for Long-Context Inference via Tailored KV Cache Optimization cites this paper.

TailorKV: A Hybrid Framework for Long-Context Inference via Tailored KV Cache Optimization GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:40.300614Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38eff18d-581c-469e-8f75-d9b88ac6bfaf · inbound

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression cites this paper.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:14.282281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d693ca11-8206-4880-b0da-41d86b5d3cf7 · inbound

TaDA: Training-free recipe for Decoding with Adaptive KV Cache Compression and Mean-centering cites this paper.

TaDA: Training-free recipe for Decoding with Adaptive KV Cache Compression and Mean-centering GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T10:45:09.879572Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5310eae0-5bb4-4afe-ac14-c9176c428768 · inbound

CaliDrop: KV Cache Compression with Calibration cites this paper.

CaliDrop: KV Cache Compression with Calibration GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T13:57:15.727858Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c0fae0e-b197-4574-816e-8b75130645d1 · inbound

CompressKV: Semantic Retrieval Heads Know What Tokens are Not Important Before Generation cites this paper.

CompressKV: Semantic Retrieval Heads Know What Tokens are Not Important Before Generation GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T05:00:04.860070Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5270e236-184d-421b-947a-e5617649799a · inbound

LMDeploy Accelerates Mixed-Precision LLM Inference with TurboMind cites this paper.

LMDeploy Accelerates Mixed-Precision LLM Inference with TurboMind GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

Reference 34

Resolution: verified exact; arxiv_id, observed 2026-05-21T22:20:42.120063Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation e588fc88-901c-4328-a74b-94078c24fee2 · inbound

PagedEviction: Structured Block-wise KV Cache Pruning for Efficient Large Language Model Inference cites this paper.

PagedEviction: Structured Block-wise KV Cache Pruning for Efficient Large Language Model Inference GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-05T10:16:13.082094Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17518d99-034c-4515-9726-e2b0bf2e9a12 · inbound

Quant VideoGen: Auto-Regressive Long Video Generation via 2-Bit KV-Cache Quantization cites this paper.

Quant VideoGen: Auto-Regressive Long Video Generation via 2-Bit KV-Cache Quantization GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-16T08:00:44.636266Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 26180e94-c9d8-4f74-b93b-983fce023816 · inbound

AdaHOP: Fast and Accurate Low-Precision Training via Outlier-Pattern-Aware Rotation cites this paper.

AdaHOP: Fast and Accurate Low-Precision Training via Outlier-Pattern-Aware Rotation GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-05-13T20:53:15.737296Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation ec38aa1a-be53-4a07-baac-d56e0703140e · inbound

Quantization Dominates Rank Reduction for KV-Cache Compression cites this paper.

Quantization Dominates Rank Reduction for KV-Cache Compression GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-11T09:56:04.560722Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation e33bd435-4711-41ab-9309-1743ef658143 · inbound

Open-TQ-Metal: Fused Compressed-Domain Attention for Long-Context LLM Inference on Apple Silicon cites this paper.

Open-TQ-Metal: Fused Compressed-Domain Attention for Long-Context LLM Inference on Apple Silicon GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

Reference 6

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T07:52:14.192689Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 8196466f-24c9-400c-b563-0b79058b682c · inbound

SAW-INT4: System-Aware 4-Bit KV-Cache Quantization for Real-World LLM Serving cites this paper.

SAW-INT4: System-Aware 4-Bit KV-Cache Quantization for Real-World LLM Serving GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-10T03:14:08.289804Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 853184f9-946d-43a3-97c6-c185c304cb92 · inbound

eOptShrinkQ: Near-Lossless KV Cache Compression Through Optimal Spectral Denoising and Quantization cites this paper.

eOptShrinkQ: Near-Lossless KV Cache Compression Through Optimal Spectral Denoising and Quantization GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-10T22:00:50.797121Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 797c33ad-141e-49f6-8239-64969751bc78 · inbound

HeadQ: Model-Visible Distortion and Score-Space Correction for KV-Cache Quantization cites this paper.

HeadQ: Model-Visible Distortion and Score-Space Correction for KV-Cache Quantization GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-12T11:01:29.722007Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation df78a131-79cd-47f3-88b3-b5c660288077 · inbound

HeadQ: Model-Visible Distortion and Score-Space Correction for KV-Cache Quantization cites this paper.

HeadQ: Model-Visible Distortion and Score-Space Correction for KV-Cache Quantization GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-09T06:20:42.525075Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 441450c7-0f1c-42e7-9131-5233b47e043f · inbound

FibQuant: Universal Vector Quantization for Random-Access KV-Cache Compression cites this paper.

FibQuant: Universal Vector Quantization for Random-Access KV-Cache Compression GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-13T01:47:04.506719Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 13fa2f57-062c-406d-be67-dd173170a9b3 · inbound

Search Your Block Floating Point Scales! cites this paper.

Search Your Block Floating Point Scales! GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

Reference 129

Resolution: verified exact; arxiv_id, observed 2026-05-13T06:02:24.096602Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation c1a85a81-d71c-4f62-829f-0e32b90b9bd7 · inbound

OSCAR: Offline Spectral Covariance-Aware Rotation for 2-bit KV Cache Quantization cites this paper.

OSCAR: Offline Spectral Covariance-Aware Rotation for 2-bit KV Cache Quantization GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

Reference 42

Resolution: verified exact; arxiv_id, observed 2026-05-20T12:18:16.457796Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation ca781ce1-a450-4219-a64e-c587edc7e076 · inbound

SPHERICAL KV: Angle-Domain Attention and Rate-Distortion Retention for Efficient Long-Context Inference cites this paper.

SPHERICAL KV: Angle-Domain Attention and Rate-Distortion Retention for Efficient Long-Context Inference GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

Reference 14

Resolution: metadata mismatch; arxiv_id, observed 2026-05-20T20:33:43.288306Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 2a04797a-b0e8-4365-b0dc-8c53e5360920 · inbound

SPHERICAL KV: Angle-Domain Attention and Rate-Distortion Retention for Efficient Long-Context Inference cites this paper.

SPHERICAL KV: Angle-Domain Attention and Rate-Distortion Retention for Efficient Long-Context Inference GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-06-30T21:35:04.844560Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation f7c3e792-1262-4343-8413-d6b058d1550a · inbound

A Simple Plug-in for Improving Eviction-Based KV Cache Compression cites this paper.

A Simple Plug-in for Improving Eviction-Based KV Cache Compression GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-05-25T04:55:24.195044Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 9303a006-593e-45b9-a8f5-a8099fd3cf29 · inbound

SPARQLe: Sub-Precision Activation Representation for Quantized LLM Inference cites this paper.

SPARQLe: Sub-Precision Activation Representation for Quantized LLM Inference GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-06-28T19:32:34.748513Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation b0381d89-0d97-4b00-8633-f384ba79211f · inbound

Cartridges at Scale: Training Modular KV Caches over Large Document Collections cites this paper.

Cartridges at Scale: Training Modular KV Caches over Large Document Collections GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

Reference 5

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T08:16:48.165901Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 50e46d3f-fb28-403a-8037-c3b8c563c7ef · inbound

HACK++: Towards More Effective Head-Aware Key-Value Compression for Efficient Visual Autoregressive Modeling cites this paper.

HACK++: Towards More Effective Head-Aware Key-Value Compression for Efficient Visual Autoregressive Modeling GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

Reference 38

Resolution: verified exact; arxiv_id, observed 2026-07-02T21:27:24.340384Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 17ab5027-5332-4216-9e0e-d8146a8dcd68 · inbound

IntentKV: Cross-Turn Intent-Aware KV Cache Pruning for Agent Inference cites this paper.

IntentKV: Cross-Turn Intent-Aware KV Cache Pruning for Agent Inference GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

Reference 11

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T20:57:22.957997Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 2783ee1a-32f5-46ff-a527-f7e05aed2797 · inbound

Kamera: Unified Position-Invariant Multimodal KV Cache for Training-Free Reuse cites this paper.

Kamera: Unified Position-Invariant Multimodal KV Cache for Training-Free Reuse GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

Reference 16

Resolution: metadata mismatch; arxiv_id, observed 2026-07-04T12:09:48.918409Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 6e81c4dd-1205-4d79-a1a9-75556b9e8042 · inbound

RoPE-Aware Bit Allocation for KV-Cache Quantization cites this paper.

RoPE-Aware Bit Allocation for KV-Cache Quantization GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-07-04T15:59:57.355432Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 95bb6d88-1f3e-47bd-8e44-4d6174afc6c8 · inbound

CompressKV: Semantic-Retrieval-Guided KV-Cache Compression for Resource-Efficient Long-Context LLM Inference cites this paper.

CompressKV: Semantic-Retrieval-Guided KV-Cache Compression for Resource-Efficient Long-Context LLM Inference GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-07-04T16:49:58.047166Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 0ed7ecab-b701-4395-bc41-f5a5b61cc369 · inbound

MosaicKV: Serving Long-Context LLM with Dynamic Two-D KV Cache Compression cites this paper.

MosaicKV: Serving Long-Context LLM with Dynamic Two-D KV Cache Compression GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

Reference 29

Resolution: verified exact; arxiv_id, observed 2026-07-02T16:17:08.402573Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 7cdd29e4-e91d-495a-807c-9983e269bd1a · inbound

From Tensor Buffer to Distributed Memory Hierarchy: A Survey of KV Cache Management for LLM Serving cites this paper.

From Tensor Buffer to Distributed Memory Hierarchy: A Survey of KV Cache Management for LLM Serving GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

Reference 56

Resolution: unresolved; no resolver link, observed 2026-07-12T09:50:23.266920Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation afa6ae33-80fd-418f-97e1-0fb83778e755 · inbound

What to Keep, What to Forget: A Rate--Distortion View of Memory Compaction in LLMs and Agents cites this paper.

What to Keep, What to Forget: A Rate--Distortion View of Memory Compaction in LLMs and Agents GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

Reference 56

Resolution: verified exact; local_arxiv, observed 2026-07-10T01:36:44.079355Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation c5c2f566-6573-44f2-83fe-7b5390964c35 · inbound

Towards Efficient Large Language Model Serving: A Survey on System-Aware KV Cache Optimization cites this paper.

Towards Efficient Large Language Model Serving: A Survey on System-Aware KV Cache Optimization GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

Reference 5

Resolution: metadata mismatch; local_arxiv, observed 2026-07-10T00:56:40.965166Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation b22813b0-b0d5-4967-9874-23a3fff43484 · inbound

Practical Online KV Cache Compaction for LLM Agents: An Empirical Study cites this paper.

Practical Online KV Cache Compaction for LLM Agents: An Empirical Study GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-06T00:48:33.732453Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 23bd3a26-47ec-430c-8306-8dc3e62b3e96 · inbound

AnchorKV: Anchor-Residual KV Cache Compression cites this paper.

AnchorKV: Anchor-Residual KV Cache Compression GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-15T15:02:52.889978Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f2f53e8-1e16-4af1-b737-44aa270e9204 · inbound

Runtime Observability for Heterogeneous Attention Memory cites this paper.

Runtime Observability for Heterogeneous Attention Memory GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T22:11:58.745454Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71aa1f3d-9747-494d-ae24-a2759075741e · inbound

CommitKV: Lifecycle-Aware KV Cache Compression via Commit Transitions for Multi-Turn Agents cites this paper.

CommitKV: Lifecycle-Aware KV Cache Compression via Commit Transitions for Multi-Turn Agents GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

Reference 103

Resolution: unresolved; no resolver link, observed 2026-08-12T00:50:51.138707Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers