HiKV: Hierarchical Importance-Aware KV Cache with Hardware Acceleration for LLM Decoding | Paper Citation Record

Observation 4a5eb13f-1a44-446a-a3a8-4ad8c73ae0c6 · outbound

This paper cites Mistral 7B.

HiKV: Hierarchical Importance-Aware KV Cache with Hardware Acceleration for LLM Decoding Mistral 7B

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-01T04:58:41.116950Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d393a459-3d3a-45d5-8569-c0bd97478b75 · outbound

This paper cites Qwen2 Technical Report.

HiKV: Hierarchical Importance-Aware KV Cache with Hardware Acceleration for LLM Decoding Qwen2 Technical Report

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-01T04:58:41.221977Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9b2bd9c-f749-42eb-9cb7-980212cc8ceb · outbound

This paper cites Llama 3 model card,.

HiKV: Hierarchical Importance-Aware KV Cache with Hardware Acceleration for LLM Decoding Llama 3 model card,

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-01T04:58:41.318115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da7909b2-9490-49a6-86de-26876e8dbc64 · outbound

This paper cites How long can context length of open-source llms truly promise?.

HiKV: Hierarchical Importance-Aware KV Cache with Hardware Acceleration for LLM Decoding How long can context length of open-source llms truly promise?

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-01T04:58:41.469197Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa6817ee-8830-46ac-a1cf-e0de2eed627d · outbound

This paper cites Language models are few-shot learners,.

HiKV: Hierarchical Importance-Aware KV Cache with Hardware Acceleration for LLM Decoding Language models are few-shot learners,

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-01T04:58:41.553081Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a9d9bc7c-6939-467d-bd4f-49f6c3eb6c83 · outbound

This paper cites Mathcoder: Seamless code integration in llms for enhanced mathematical reasoning,.

HiKV: Hierarchical Importance-Aware KV Cache with Hardware Acceleration for LLM Decoding Mathcoder: Seamless code integration in llms for enhanced mathematical reasoning,

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-01T04:58:41.719217Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 265aae74-fe63-4ce2-bff8-76c421346c67 · outbound

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

HiKV: Hierarchical Importance-Aware KV Cache with Hardware Acceleration for LLM Decoding Longbench: A bilingual, multitask benchmark for long context understanding,

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-01T04:58:41.837251Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b66a1dd3-0fe1-46a0-9064-8ec084fbd602 · outbound

This paper cites P3-llm: An integrated npu-pim accelerator for llm inference using hybrid numerical formats,.

HiKV: Hierarchical Importance-Aware KV Cache with Hardware Acceleration for LLM Decoding P3-llm: An integrated npu-pim accelerator for llm inference using hybrid numerical formats,

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-01T04:58:41.915830Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64458efa-d583-4833-b270-826b924a6558 · outbound

This paper cites A survey on large language model acceleration based on kv cache management,.

HiKV: Hierarchical Importance-Aware KV Cache with Hardware Acceleration for LLM Decoding A survey on large language model acceleration based on kv cache management,

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-01T04:58:42.060439Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1efbd9f7-260f-488c-b7d1-d0c26ae5ee0b · outbound

This paper cites Codec: Prefix-shared decoding kernel for llms,.

HiKV: Hierarchical Importance-Aware KV Cache with Hardware Acceleration for LLM Decoding Codec: Prefix-shared decoding kernel for llms,

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-01T04:58:42.210027Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7ddd9b6-e43d-45d6-aeea-f49e8bbffe2f · outbound

This paper cites Orca: A distributed serving system for transformer- based generative models,.

HiKV: Hierarchical Importance-Aware KV Cache with Hardware Acceleration for LLM Decoding Orca: A distributed serving system for transformer- based generative models,

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-01T04:58:42.300437Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2bc9d2b-61b4-461b-8350-8052822ef91a · outbound

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

HiKV: Hierarchical Importance-Aware KV Cache with Hardware Acceleration for LLM Decoding Splitwise: Efficient generative llm inference using phase splitting,

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-01T04:58:42.410203Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91226077-408b-4a62-8895-c59e6dead0e7 · outbound

This paper cites Kivi: A tuning-free asymmetric 2bit quantization for kv cache,.

HiKV: Hierarchical Importance-Aware KV Cache with Hardware Acceleration for LLM Decoding Kivi: A tuning-free asymmetric 2bit quantization for kv cache,

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-01T04:58:42.511116Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9444d6e0-37ff-4da2-b119-2d5ac9ffbcad · outbound

This paper cites Efficient streaming language models with attention sinks,.

HiKV: Hierarchical Importance-Aware KV Cache with Hardware Acceleration for LLM Decoding Efficient streaming language models with attention sinks,

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-01T04:58:42.619086Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64b35529-fa0f-45f7-9700-bc509221e412 · outbound

This paper cites Duoattention: Efficient long-context llm inference with retrieval and streaming heads,.

HiKV: Hierarchical Importance-Aware KV Cache with Hardware Acceleration for LLM Decoding Duoattention: Efficient long-context llm inference with retrieval and streaming heads,

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-01T04:58:42.712200Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17e9a2ab-f619-4ccc-8439-672908bf54cf · outbound

This paper cites Snapkv: Llm knows what you are looking for before gener- ation,.

HiKV: Hierarchical Importance-Aware KV Cache with Hardware Acceleration for LLM Decoding Snapkv: Llm knows what you are looking for before gener- ation,

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-01T04:58:42.821069Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f01aef9d-f544-4f9e-81b1-22137343fa9d · outbound

This paper cites Sepllm: Accelerate large language models by com- pressing one segment into one separator,.

HiKV: Hierarchical Importance-Aware KV Cache with Hardware Acceleration for LLM Decoding Sepllm: Accelerate large language models by com- pressing one segment into one separator,

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-01T04:58:42.925778Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71c03b91-62dc-4df3-88b6-452aaa2d9d7b · outbound

This paper cites Lm-infinite: Zero-shot extreme length generalization for large language models,.

HiKV: Hierarchical Importance-Aware KV Cache with Hardware Acceleration for LLM Decoding Lm-infinite: Zero-shot extreme length generalization for large language models,

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-01T04:58:42.999165Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f39ce39-6cc0-495b-966b-d541fcf165f6 · outbound

This paper cites Longformer: The Long-Document Transformer.

HiKV: Hierarchical Importance-Aware KV Cache with Hardware Acceleration for LLM Decoding Longformer: The Long-Document Transformer

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-01T04:58:43.070342Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 23a69917-216f-40a3-b323-06d044da6719 · outbound

This paper cites H2o: Heavy-hitter oracle for efficient generative inference of large language models,.

HiKV: Hierarchical Importance-Aware KV Cache with Hardware Acceleration for LLM Decoding H2o: Heavy-hitter oracle for efficient generative inference of large language models,

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-01T04:58:43.182267Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54487552-cbc4-45c4-a1d4-2f33166ce04a · outbound

This paper cites Scissorhands: Exploiting the persistence of importance hypothesis for llm kv cache compression at test time,.

HiKV: Hierarchical Importance-Aware KV Cache with Hardware Acceleration for LLM Decoding Scissorhands: Exploiting the persistence of importance hypothesis for llm kv cache compression at test time,

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-01T04:58:43.305148Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 318a4ef6-4f36-4e23-939a-687ecb7d8edd · outbound

This paper cites Kvo-llm: Boosting long-context generation throughput for batched llm inference,.

HiKV: Hierarchical Importance-Aware KV Cache with Hardware Acceleration for LLM Decoding Kvo-llm: Boosting long-context generation throughput for batched llm inference,

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-01T04:58:43.394240Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e2cabfc-b120-4daf-86f8-207a0a322d8b · outbound

This paper cites Keyformer: Kv cache reduction through key tokens selection for efficient generative inference,.

HiKV: Hierarchical Importance-Aware KV Cache with Hardware Acceleration for LLM Decoding Keyformer: Kv cache reduction through key tokens selection for efficient generative inference,

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-01T04:58:43.506772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 313f3b18-dce6-4810-b5ce-f1a393fa2957 · outbound

This paper cites Alisa: Accelerating large language model inference via sparsity-aware kv caching,.

HiKV: Hierarchical Importance-Aware KV Cache with Hardware Acceleration for LLM Decoding Alisa: Accelerating large language model inference via sparsity-aware kv caching,

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-01T04:58:43.606157Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d78b5e8-4f14-4873-93fa-b52b7a00c4d3 · outbound

This paper cites Mata: A memory-efficient attention accelerator for llms exploiting look-back kv cache pruning,.

HiKV: Hierarchical Importance-Aware KV Cache with Hardware Acceleration for LLM Decoding Mata: A memory-efficient attention accelerator for llms exploiting look-back kv cache pruning,

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-01T04:58:43.696933Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88bcf029-6fc7-4492-8f9d-7280cd5933e4 · outbound

This paper cites Unicaim: A unified cam/cim architecture with static- dynamic kv cache pruning for efficient long-context llm inference,.

HiKV: Hierarchical Importance-Aware KV Cache with Hardware Acceleration for LLM Decoding Unicaim: A unified cam/cim architecture with static- dynamic kv cache pruning for efficient long-context llm inference,

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-01T04:58:43.829479Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d746782c-237a-4ea6-850b-e105d2e2bfc5 · outbound

This paper cites Token-picker: Accelerating attention in text generation with minimized memory transfer via probability estimation,.

HiKV: Hierarchical Importance-Aware KV Cache with Hardware Acceleration for LLM Decoding Token-picker: Accelerating attention in text generation with minimized memory transfer via probability estimation,

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-01T04:58:43.934750Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79c477fa-51e5-4b0a-8746-14a8ec912734 · outbound

This paper cites Dias: Distance-based attention sparsity for ultra-long- sequence transformer with tree-like processing-in-memory architecture,.

HiKV: Hierarchical Importance-Aware KV Cache with Hardware Acceleration for LLM Decoding Dias: Distance-based attention sparsity for ultra-long- sequence transformer with tree-like processing-in-memory architecture,

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-01T04:58:44.011211Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd5d4989-9e38-45d6-93e6-795bbd388645 · outbound

This paper cites Veda: Efficient llm generation through voting-based kv cache eviction and dataflow-flexible accelerator,.

HiKV: Hierarchical Importance-Aware KV Cache with Hardware Acceleration for LLM Decoding Veda: Efficient llm generation through voting-based kv cache eviction and dataflow-flexible accelerator,

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-01T04:58:44.075196Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20e531de-bec9-4f9a-b671-a9e308b1d187 · outbound

This paper cites Kv-cache oriented query-aware sparse attention accelerator with cross-stage precision-configurable digital cim,.

HiKV: Hierarchical Importance-Aware KV Cache with Hardware Acceleration for LLM Decoding Kv-cache oriented query-aware sparse attention accelerator with cross-stage precision-configurable digital cim,

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-01T04:58:44.170208Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc0f6cc6-865f-4b67-af00-7818900e3b05 · outbound

This paper cites End-to-end acceleration of generative models with runtime regularized kv cache management,.

HiKV: Hierarchical Importance-Aware KV Cache with Hardware Acceleration for LLM Decoding End-to-end acceleration of generative models with runtime regularized kv cache management,

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-01T04:58:44.321904Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation deeb2018-df6f-49d8-af1b-701c3b66cca0 · outbound

This paper cites Edgellm: A highly efficient cpu-fpga heterogeneous edge accelerator for large language models,.

HiKV: Hierarchical Importance-Aware KV Cache with Hardware Acceleration for LLM Decoding Edgellm: A highly efficient cpu-fpga heterogeneous edge accelerator for large language models,

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-01T04:58:44.430466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 082819a2-cf6e-4748-b2e9-7663597bb079 · outbound

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

HiKV: Hierarchical Importance-Aware KV Cache with Hardware Acceleration for LLM Decoding Distserve: Disaggregating prefill and decoding for goodput-optimized large language model serving,

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-01T04:58:44.529874Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 63bd56cf-985d-4172-ba8b-b72d0e54149a · outbound

This paper cites Flightllm: Efficient large language model inference with a complete mapping flow on fpgas,.

HiKV: Hierarchical Importance-Aware KV Cache with Hardware Acceleration for LLM Decoding Flightllm: Efficient large language model inference with a complete mapping flow on fpgas,

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-01T04:58:44.760684Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f0df5c5-732d-48a8-902d-ee7f519581f4 · outbound

This paper cites Ofq-llm: Outlier-flexing quantization for efficient low- bit large language model acceleration,.

HiKV: Hierarchical Importance-Aware KV Cache with Hardware Acceleration for LLM Decoding Ofq-llm: Outlier-flexing quantization for efficient low- bit large language model acceleration,

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-01T04:58:44.943518Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca253343-8b28-448c-901b-7b5abf8a5582 · outbound

This paper cites Kv cache compression, but what must we give in return? a comprehensive benchmark of long context capable approaches,.

HiKV: Hierarchical Importance-Aware KV Cache with Hardware Acceleration for LLM Decoding Kv cache compression, but what must we give in return? a comprehensive benchmark of long context capable approaches,

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-01T04:58:45.144166Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e20f6a49-0c49-43c5-94ad-f2b9c415ab98 · outbound

This paper cites Apt-llm: Exploiting arbitrary-precision tensor core comput- ing for llm acceleration,.

HiKV: Hierarchical Importance-Aware KV Cache with Hardware Acceleration for LLM Decoding Apt-llm: Exploiting arbitrary-precision tensor core comput- ing for llm acceleration,

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-01T04:58:45.303812Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation abc3d7e8-46f9-48a6-b05e-c1b19e0be6fb · outbound

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

HiKV: Hierarchical Importance-Aware KV Cache with Hardware Acceleration for LLM Decoding A Survey on Efficient Inference for Large Language Models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-01T04:58:45.474492Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b3a0208c-2ad0-46de-b0b8-7c0713d15844 · outbound

This paper cites When to stop? towards efficient code generation in llms with excess token prevention,.

HiKV: Hierarchical Importance-Aware KV Cache with Hardware Acceleration for LLM Decoding When to stop? towards efficient code generation in llms with excess token prevention,

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-01T04:58:45.605674Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d6ec201e-38ec-4d68-a31d-44fe07b3fea5 · outbound

This paper cites Llmcompass: Enabling efficient hardware design for large language model inference,.

HiKV: Hierarchical Importance-Aware KV Cache with Hardware Acceleration for LLM Decoding Llmcompass: Enabling efficient hardware design for large language model inference,

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-01T04:58:45.795483Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 604e267d-01bf-49e1-805d-3ab2733c5df8 · outbound

This paper cites Energy cost modelling for optimizing large language model inference on hardware accelerators,.

HiKV: Hierarchical Importance-Aware KV Cache with Hardware Acceleration for LLM Decoding Energy cost modelling for optimizing large language model inference on hardware accelerators,

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-01T04:58:46.038243Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9168e695-d063-4ad4-9634-4fa85f8a9393 · outbound

This paper cites LLM Inference Unveiled: Survey and Roofline Model Insights.

HiKV: Hierarchical Importance-Aware KV Cache with Hardware Acceleration for LLM Decoding LLM Inference Unveiled: Survey and Roofline Model Insights

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-01T04:58:46.181845Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89491f21-4613-47d2-8be2-e7c1ee4649b6 · outbound

This paper cites Skipkv: Selective skipping of kv generation and storage for efficient inference with large reasoning models,.

HiKV: Hierarchical Importance-Aware KV Cache with Hardware Acceleration for LLM Decoding Skipkv: Selective skipping of kv generation and storage for efficient inference with large reasoning models,

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-01T04:58:46.374845Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a0e496a-1570-4ff2-900b-8d6699310dce · outbound

This paper cites Titanus: Enabling kv cache pruning and quantization on-the-fly for llm acceleration,.

HiKV: Hierarchical Importance-Aware KV Cache with Hardware Acceleration for LLM Decoding Titanus: Enabling kv cache pruning and quantization on-the-fly for llm acceleration,

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-01T04:58:46.548695Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 605bc04d-cf93-41d7-a727-1a6322b69f05 · outbound

This paper cites Infinigen: Efficient generative inference of large language models with dynamic kv cache management,.

HiKV: Hierarchical Importance-Aware KV Cache with Hardware Acceleration for LLM Decoding Infinigen: Efficient generative inference of large language models with dynamic kv cache management,

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-01T04:58:46.763518Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3fe095db-cf41-4bfe-b822-d71c0a6c13f6 · outbound

This paper cites Sparq attention: Bandwidth-efficient llm inference,.

HiKV: Hierarchical Importance-Aware KV Cache with Hardware Acceleration for LLM Decoding Sparq attention: Bandwidth-efficient llm inference,

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-01T04:58:47.016141Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 610a51a3-5140-4cf8-873c-e171f7a54f2f · outbound

This paper cites Algorithm 232: Heapsort,.

HiKV: Hierarchical Importance-Aware KV Cache with Hardware Acceleration for LLM Decoding Algorithm 232: Heapsort,

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-01T04:58:47.163798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f3832966-788f-4656-a365-4e0ff33f09a0 · outbound

This paper cites Sorting networks and their applications,.

HiKV: Hierarchical Importance-Aware KV Cache with Hardware Acceleration for LLM Decoding Sorting networks and their applications,

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-01T04:58:47.269194Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1da2e8d6-b1c9-4d46-ab3b-8d346b62474f · outbound

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

HiKV: Hierarchical Importance-Aware KV Cache with Hardware Acceleration for LLM Decoding Efficient memory management for large language model serving with PagedAttention,

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-01T04:58:47.421112Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5bbae7ab-3070-43ee-8ecf-b4e80e042fe3 · outbound

This paper cites Anda: Unlocking efficient llm inference with a variable- length grouped activation data format,.

HiKV: Hierarchical Importance-Aware KV Cache with Hardware Acceleration for LLM Decoding Anda: Unlocking efficient llm inference with a variable- length grouped activation data format,

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-01T04:58:47.516573Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef6216b1-3f70-4659-8ed8-230610832737 · outbound

This paper cites Ten lessons from three generations shaped google’s tpuv4i: Industrial product,.

HiKV: Hierarchical Importance-Aware KV Cache with Hardware Acceleration for LLM Decoding Ten lessons from three generations shaped google’s tpuv4i: Industrial product,

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-01T04:58:47.631238Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab6c5676-5725-4df3-8714-ccfd8c9d5462 · outbound

This paper cites Dramsim3: A cycle-accurate, thermal-capable dram sim- ulator,.

HiKV: Hierarchical Importance-Aware KV Cache with Hardware Acceleration for LLM Decoding Dramsim3: A cycle-accurate, thermal-capable dram sim- ulator,

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-01T04:58:47.771700Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d45b6d6-2d5b-49e7-83f1-77b9cf4008f3 · outbound

This paper cites Ada-kv: Optimizing kv cache eviction by adaptive budget allocation for efficient llm inference,.

HiKV: Hierarchical Importance-Aware KV Cache with Hardware Acceleration for LLM Decoding Ada-kv: Optimizing kv cache eviction by adaptive budget allocation for efficient llm inference,

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-01T04:58:47.864332Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 469204c9-e339-46d2-a2b8-a54f42bcba56 · outbound

This paper cites Dynamickv: Task-aware adaptive kv cache compression for long context llms,.

HiKV: Hierarchical Importance-Aware KV Cache with Hardware Acceleration for LLM Decoding Dynamickv: Task-aware adaptive kv cache compression for long context llms,

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-01T04:58:47.969320Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9345b92f-f78d-4469-8e47-d447e96ef55d · outbound

This paper cites DeepScaleTool: A tool for the accurate estimation of technology scaling in the deep-submicron era,.

HiKV: Hierarchical Importance-Aware KV Cache with Hardware Acceleration for LLM Decoding DeepScaleTool: A tool for the accurate estimation of technology scaling in the deep-submicron era,

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-01T04:58:48.072701Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers