Paper Citation Record · LEDGER

PowerInfer-2: Fast Large Language Model Inference on a Smartphone

As of 18 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 42 inbound Pith citation observations for arXiv:2406.06282.

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

pith.paper-citation-record.v1
2406.06282 v3

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 42 of 42 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+00:00

measured 42 of 42 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-16T05:09:55.031898Z

measured 1 of 1 external citation measurements

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

Source: pith, observed 2026-08-05T02:28:24.338817Z

Reference resolution

0 of 0 outbound references displayed

verified exact0
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

5
pith, observed 2026-08-05T02:28:24.338817Z

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation 456d174e-001a-4ade-b2fd-533489973d47 · inbound

BlueLM-V-3B: Algorithm and System Co-Design for Multimodal Large Language Models on Mobile Devices cites this paper.

BlueLM-V-3B: Algorithm and System Co-Design for Multimodal Large Language Models on Mobile Devices PowerInfer-2: Fast Large Language Model Inference on a Smartphone

Reference 132

Resolution: unresolved; no resolver link, observed 2026-08-12T19:33:01.033890Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c7d2330-15c8-4845-b7b3-f9906a84d1b9 · inbound

Efficient LLM Inference using Dynamic Input Pruning and Cache-Aware Masking cites this paper.

Efficient LLM Inference using Dynamic Input Pruning and Cache-Aware Masking PowerInfer-2: Fast Large Language Model Inference on a Smartphone

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-12T04:30:36.119613Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0aac06a-5260-43f4-bdb5-24caff9e8358 · inbound

Densing Law of LLMs cites this paper.

Densing Law of LLMs PowerInfer-2: Fast Large Language Model Inference on a Smartphone

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-11T21:40:05.602148Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c569c36-6cf0-4a3b-8347-14970b0e2415 · inbound

IC-Cache: Efficient Large Language Model Serving via In-context Caching cites this paper.

IC-Cache: Efficient Large Language Model Serving via In-context Caching PowerInfer-2: Fast Large Language Model Inference on a Smartphone

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-10T16:59:01.428571Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73483b14-f398-4fdc-ae5e-94611d77db4d · inbound

iServe: An Intent-based Serving System for LLMs cites this paper.

iServe: An Intent-based Serving System for LLMs PowerInfer-2: Fast Large Language Model Inference on a Smartphone

Reference 120

Resolution: unresolved; no resolver link, observed 2026-08-10T21:37:14.534676Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 339db099-dd19-46ef-be92-964ead0a53a3 · inbound

Scaling On-Device GPU Inference for Large Generative Models cites this paper.

Scaling On-Device GPU Inference for Large Generative Models PowerInfer-2: Fast Large Language Model Inference on a Smartphone

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-16T04:51:31.537714Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b03021e-085b-46b0-b834-2a12b430ecde · inbound

Responsive DNN Adaptation for Video Analytics against Environment Shift via Hierarchical Mobile-Cloud Collaborations cites this paper.

Responsive DNN Adaptation for Video Analytics against Environment Shift via Hierarchical Mobile-Cloud Collaborations PowerInfer-2: Fast Large Language Model Inference on a Smartphone

Reference 81

Resolution: unresolved; no resolver link, observed 2026-08-16T05:09:55.031898Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46a15fe9-ec8e-41b3-98e1-6d898f5b7c49 · inbound

RetroInfer: A Vector Storage Engine for Scalable Long-Context LLM Inference cites this paper.

RetroInfer: A Vector Storage Engine for Scalable Long-Context LLM Inference PowerInfer-2: Fast Large Language Model Inference on a Smartphone

Reference 111

Resolution: metadata mismatch; arxiv_id, observed 2026-05-09T06:35:24.624547Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation fc9a2071-2c3c-4899-ad54-d6cbf007e740 · inbound

FloE: On-the-Fly MoE Inference on Memory-constrained GPU cites this paper.

FloE: On-the-Fly MoE Inference on Memory-constrained GPU PowerInfer-2: Fast Large Language Model Inference on a Smartphone

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-15T23:00:18.153988Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f5c1124-bece-4e9b-a235-fd754a1aaa5e · inbound

CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models cites this paper.

CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models PowerInfer-2: Fast Large Language Model Inference on a Smartphone

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-07T14:26:17.250081Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f3dcdbe-99c7-4bea-9254-fdd19144a1cb · inbound

TensorShield: Safeguarding On-Device Inference by Shielding Critical DNN Tensors with TEE cites this paper.

TensorShield: Safeguarding On-Device Inference by Shielding Critical DNN Tensors with TEE PowerInfer-2: Fast Large Language Model Inference on a Smartphone

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-07T13:08:01.749848Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6491a2a5-891d-4668-ac7c-12812760b38b · inbound

Small Language Models are the Future of Agentic AI cites this paper.

Small Language Models are the Future of Agentic AI PowerInfer-2: Fast Large Language Model Inference on a Smartphone

Reference 78

Resolution: verified exact; arxiv_id, observed 2026-05-16T11:55:51.043385Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation feb5f522-870d-4ed0-a219-fdf23f4847e2 · inbound

MoQAE: Mixed-Precision Quantization for Long-Context LLM Inference via Mixture of Quantization-Aware Experts cites this paper.

MoQAE: Mixed-Precision Quantization for Long-Context LLM Inference via Mixture of Quantization-Aware Experts PowerInfer-2: Fast Large Language Model Inference on a Smartphone

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T05:37:52.808116Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6af74b8a-00e2-4fe4-9dec-a48a499e844f · inbound

DIVE into MoE: Diversity-Enhanced Reconstruction of Large Language Models from Dense into Mixture-of-Experts cites this paper.

DIVE into MoE: Diversity-Enhanced Reconstruction of Large Language Models from Dense into Mixture-of-Experts PowerInfer-2: Fast Large Language Model Inference on a Smartphone

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-07T04:59:18.087086Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dfe72331-8322-4198-ad01-cb3db0095e9a · inbound

MNN-LLM: A Generic Inference Engine for Fast Large Language Model Deployment on Mobile Devices cites this paper.

MNN-LLM: A Generic Inference Engine for Fast Large Language Model Deployment on Mobile Devices PowerInfer-2: Fast Large Language Model Inference on a Smartphone

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-07T04:33:41.493324Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 04ba6675-87b1-4c23-b053-d03152eb5e06 · inbound

SparseLoRA: Accelerating LLM Fine-Tuning with Contextual Sparsity cites this paper.

SparseLoRA: Accelerating LLM Fine-Tuning with Contextual Sparsity PowerInfer-2: Fast Large Language Model Inference on a Smartphone

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-15T19:30:31.172365Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 53e72b54-46d4-42fd-8b28-627f600ef4c0 · inbound

MNN-AECS: Energy Optimization for LLM Decoding on Mobile Devices via Adaptive Core Selection cites this paper.

MNN-AECS: Energy Optimization for LLM Decoding on Mobile Devices via Adaptive Core Selection PowerInfer-2: Fast Large Language Model Inference on a Smartphone

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-15T18:40:01.498224Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 53927732-1194-40e3-ba29-008579fe1cf7 · inbound

Dissecting the Impact of Mobile DVFS Governors on LLM Inference Performance and Energy Efficiency cites this paper.

Dissecting the Impact of Mobile DVFS Governors on LLM Inference Performance and Energy Efficiency PowerInfer-2: Fast Large Language Model Inference on a Smartphone

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-06T20:44:17.762246Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b428182-fc7c-427b-a729-c682db3579a5 · inbound

Efficient Deployment of Vision-Language Models on Mobile Devices: A Case Study on OnePlus 13R cites this paper.

Efficient Deployment of Vision-Language Models on Mobile Devices: A Case Study on OnePlus 13R PowerInfer-2: Fast Large Language Model Inference on a Smartphone

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-06T18:20:53.546644Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3bd469b-6ec3-40fb-a33e-85f97cc595f6 · inbound

BlockFFN: Towards End-Side Acceleration-Friendly Mixture-of-Experts with Chunk-Level Activation Sparsity cites this paper.

BlockFFN: Towards End-Side Acceleration-Friendly Mixture-of-Experts with Chunk-Level Activation Sparsity PowerInfer-2: Fast Large Language Model Inference on a Smartphone

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-06T18:20:00.457313Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dbb96f30-34c4-438f-addc-dc9902738ff9 · inbound

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning cites this paper.

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning PowerInfer-2: Fast Large Language Model Inference on a Smartphone

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-06T05:36:21.155515Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab19481e-dffc-40bc-96bd-7084443c15c4 · inbound

ShadowNPU: System and Algorithm Co-design for NPU-Centric On-Device LLM Inference cites this paper.

ShadowNPU: System and Algorithm Co-design for NPU-Centric On-Device LLM Inference PowerInfer-2: Fast Large Language Model Inference on a Smartphone

Reference 71

Resolution: verified exact; arxiv_id, observed 2026-05-18T22:06:52.141041Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 8ad5e15e-bae3-48a4-968e-90f9a3b25f4d · inbound

WISP: Waste- and Interference-Suppressed Distributed Speculative LLM Serving at the Edge via Dynamic Drafting and SLO-Aware Batching cites this paper.

WISP: Waste- and Interference-Suppressed Distributed Speculative LLM Serving at the Edge via Dynamic Drafting and SLO-Aware Batching PowerInfer-2: Fast Large Language Model Inference on a Smartphone

Reference 33

Resolution: verified exact; arxiv_id, observed 2026-05-16T14:12:58.650668Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 61e88517-3136-4dab-8730-5c9978488b2c · inbound

Understanding User Privacy Perceptions of GenAI Smartphones cites this paper.

Understanding User Privacy Perceptions of GenAI Smartphones PowerInfer-2: Fast Large Language Model Inference on a Smartphone

Reference 79

Resolution: verified exact; arxiv_id, observed 2026-05-10T23:10:51.598346Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation a3e0deb1-2816-4836-8266-7be16572cec3 · inbound

MCAP: Deployment-Time Layer Profiling for Memory-Constrained LLM Inference cites this paper.

MCAP: Deployment-Time Layer Profiling for Memory-Constrained LLM Inference PowerInfer-2: Fast Large Language Model Inference on a Smartphone

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-10T00:54:48.401477Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation ac7eb187-db2c-43fb-85a5-6fe3d9f45801 · inbound

EdgeFM: Efficient Edge Inference for Vision-Language Models cites this paper.

EdgeFM: Efficient Edge Inference for Vision-Language Models PowerInfer-2: Fast Large Language Model Inference on a Smartphone

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-12T10:01:27.717820Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 5caa659d-b24b-4210-823e-f444f7ed121d · inbound

EdgeFM: Efficient Edge Inference for Vision-Language Models cites this paper.

EdgeFM: Efficient Edge Inference for Vision-Language Models PowerInfer-2: Fast Large Language Model Inference on a Smartphone

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-07-01T08:55:34.742443Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 1d99e954-1e6b-495a-b3a5-5857d15d1b5d · inbound

Lever: Speculative LLM Inference on Smartphones cites this paper.

Lever: Speculative LLM Inference on Smartphones PowerInfer-2: Fast Large Language Model Inference on a Smartphone

Reference 36

Resolution: verified exact; arxiv_id, observed 2026-05-19T21:47:48.483707Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation e6e60fec-694c-40db-a75a-e7b687591a5c · inbound

When NPUs Are Not Always Faster: A Stage-Level Analysis of Mobile LLM Inference cites this paper.

When NPUs Are Not Always Faster: A Stage-Level Analysis of Mobile LLM Inference PowerInfer-2: Fast Large Language Model Inference on a Smartphone

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-06-30T15:04:46.182427Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation af2b36e5-e4b7-4408-bc44-cfb1e0fbb080 · inbound

TileFuse: A Fused Mixed-Precision Kernel Library for Efficient Quantized LLM Inference on AMD NPUs cites this paper.

TileFuse: A Fused Mixed-Precision Kernel Library for Efficient Quantized LLM Inference on AMD NPUs PowerInfer-2: Fast Large Language Model Inference on a Smartphone

Reference 56

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T07:57:44.941264Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 1a444fdc-ed0e-44c7-a1b4-b1cc05198f42 · inbound

TileFuse: A Fused Mixed-Precision Kernel Library for Efficient Quantized LLM Inference on AMD NPUs cites this paper.

TileFuse: A Fused Mixed-Precision Kernel Library for Efficient Quantized LLM Inference on AMD NPUs PowerInfer-2: Fast Large Language Model Inference on a Smartphone

Reference 56

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T23:39:02.905070Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 071dec5c-0a4d-49ed-b77c-d6b98206327d · inbound

Does Mixture-of-Experts Actually Help Inference on Consumer and Edge Hardware? An Empirical Study cites this paper.

Does Mixture-of-Experts Actually Help Inference on Consumer and Edge Hardware? An Empirical Study PowerInfer-2: Fast Large Language Model Inference on a Smartphone

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-07-04T07:59:39.607441Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 38bbb818-13f7-46c1-afa4-c6412830500d · inbound

Does Mixture-of-Experts Actually Help Inference on Consumer and Edge Hardware? An Empirical Study cites this paper.

Does Mixture-of-Experts Actually Help Inference on Consumer and Edge Hardware? An Empirical Study PowerInfer-2: Fast Large Language Model Inference on a Smartphone

Reference 27

Resolution: unresolved; no resolver link, observed 2026-07-12T13:05:17.273287Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4708dba-eaae-4573-9c1b-af9c4fd2dc6b · inbound

Enabling Cloud-Level Accuracy in Edge AI through IoT Data Preprocessing cites this paper.

Enabling Cloud-Level Accuracy in Edge AI through IoT Data Preprocessing PowerInfer-2: Fast Large Language Model Inference on a Smartphone

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-07-04T09:49:44.091015Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 02212a14-d014-4c2e-9473-8d7696156391 · inbound

EnerInfer: Energy-Aware On-Device LLM Inference cites this paper.

EnerInfer: Energy-Aware On-Device LLM Inference PowerInfer-2: Fast Large Language Model Inference on a Smartphone

Reference 71

Resolution: verified exact; arxiv_id, observed 2026-07-04T11:29:50.714252Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 9cd432d8-7f33-45ec-a4fb-8fb12919a0e3 · inbound

Is Your NPU Ready for LLMs? Dissecting the Hidden Efficiency Bottlenecks in Mobile LLM Inference cites this paper.

Is Your NPU Ready for LLMs? Dissecting the Hidden Efficiency Bottlenecks in Mobile LLM Inference PowerInfer-2: Fast Large Language Model Inference on a Smartphone

Reference 7

Resolution: unresolved; no resolver link, observed 2026-07-11T12:14:57.342551Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 868c65d1-9304-493d-af0e-5d65aefd8baf · inbound

Voltron: Enabling Elastic Multi-Device Execution of LLM Inference for Empowered Edge Intelligence cites this paper.

Voltron: Enabling Elastic Multi-Device Execution of LLM Inference for Empowered Edge Intelligence PowerInfer-2: Fast Large Language Model Inference on a Smartphone

Reference 67

Resolution: verified exact; local_arxiv, observed 2026-07-09T21:16:34.319320Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 6db40602-1fd7-4e89-b1d1-26327047031e · inbound

HeteroMosaic: Exposing and Exploiting Heterogeneous Execution Opportunities for Energy-Efficient Edge LLM Inference cites this paper.

HeteroMosaic: Exposing and Exploiting Heterogeneous Execution Opportunities for Energy-Efficient Edge LLM Inference PowerInfer-2: Fast Large Language Model Inference on a Smartphone

Reference 90

Resolution: unresolved; no resolver link, observed 2026-08-02T06:22:22.488014Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c38e300-665a-4aef-a38d-3b57963224b7 · inbound

Transition-Aware Backend Dispatch for Edge LLM Inference cites this paper.

Transition-Aware Backend Dispatch for Edge LLM Inference PowerInfer-2: Fast Large Language Model Inference on a Smartphone

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-01T18:04:57.453503Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88c1eab1-7bb5-4783-88e3-211bbbeb280d · inbound

SelectInfer: Selective Neuron Loading and Computation for On-Device LLMs cites this paper.

SelectInfer: Selective Neuron Loading and Computation for On-Device LLMs PowerInfer-2: Fast Large Language Model Inference on a Smartphone

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-01T16:14:37.007544Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57cc3a2f-510a-4154-936f-42009b093336 · inbound

SparSEEty: Extracting Tokens from Sparsity-Exploiting LLM Serving Systems via Deterministic Side Channels cites this paper.

SparSEEty: Extracting Tokens from Sparsity-Exploiting LLM Serving Systems via Deterministic Side Channels PowerInfer-2: Fast Large Language Model Inference on a Smartphone

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-08T04:21:30.070796Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38c75e83-06e6-482d-a605-704dc4492a13 · inbound

The Ingestion Tax: Adopting File-Backed Weights in Tensor Frameworks cites this paper.

The Ingestion Tax: Adopting File-Backed Weights in Tensor Frameworks PowerInfer-2: Fast Large Language Model Inference on a Smartphone

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-16T00:22:44.065594Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.