Paper Citation Record · LEDGER

MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design

As of 16 August 2026, this Paper Citation Record lists 34 of 34 outbound references and 8 inbound Pith citation observations for arXiv:2505.05799.

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

pith.paper-citation-record.v1
2505.05799 v1

Coverage vector

measured 34 of 34 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T23:01:20.181224Z

measured 42 of 42 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-16T06:30:59.297886+00:00

measured 8 of 8 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T14:44:23.206783Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-02T07:06:44.791368Z

Reference resolution

34 of 34 outbound references displayed

verified exact0
verified fuzzy7
unresolved27
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation fae7f16a-4076-4d7c-b3ac-4397f61496f8 · outbound

This paper cites QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs.

MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-15T23:01:20.057459Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 442e46a2-6bc2-411c-84c1-41317f8a6c3e · outbound

This paper cites Low-bit quantization of neural networks for efficient inference.

MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design Low-bit quantization of neural networks for efficient inference

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:01:20.523687Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 2bbf663d-b615-4203-9c62-2ac844c7cb79 · outbound

This paper cites an unresolved cited work.

MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design Unresolved cited work

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-15T23:01:20.065538Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13d58736-2609-45fd-a29c-c156249b2ea0 · outbound

This paper cites W., and Keutzer, K.

MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design W., and Keutzer, K

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:01:20.506413Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 3401228c-f079-463d-ada3-8a6ca46e1288 · outbound

This paper cites SKVQ: Sliding-window Key and Value Cache Quantization for Large Language Models.

MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design SKVQ: Sliding-window Key and Value Cache Quantization for Large Language Models

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-15T23:01:20.073536Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c448d4d-c0f8-492a-94d2-40e883942945 · outbound

This paper cites GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers.

MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-15T23:01:20.077587Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d60be69-3fb9-49a9-b18a-05b46e5b8c58 · outbound

This paper cites MARLIN: Mixed-Precision Auto-Regressive Parallel Inference on Large Language Models.

MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design MARLIN: Mixed-Precision Auto-Regressive Parallel Inference on Large Language Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-15T23:01:20.081983Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 953946d5-49a6-46f0-b501-a78f5152ee61 · outbound

This paper cites Bounds on multiprocessing timing anomalies.

MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design Bounds on multiprocessing timing anomalies

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:01:20.494395Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation e648adde-0231-4344-914a-9972409ac979 · outbound

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

MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-15T23:01:20.089202Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 029dab77-d234-4476-b5fd-912743227866 · outbound

This paper cites Mixture Compressor for Mixture-of-Experts LLMs Gains More.

MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design Mixture Compressor for Mixture-of-Experts LLMs Gains More

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-15T23:01:20.093251Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b93a2e4-05c1-46cd-afb1-76b41fa05113 · outbound

This paper cites Mixtral of Experts.

MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design Mixtral of Experts

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-15T23:01:20.097145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 41c61031-866a-4907-bf8c-50104bd6c46d · outbound

This paper cites SqueezeLLM: Dense-and-Sparse Quantization.

MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design SqueezeLLM: Dense-and-Sparse Quantization

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-15T23:01:20.100645Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d6270ae-746d-425f-beab-4b82702672fd · outbound

This paper cites Who Says Elephants Can't Run: Bringing Large Scale MoE Models into Cloud Scale Production.

MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design Who Says Elephants Can't Run: Bringing Large Scale MoE Models into Cloud Scale Production

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-15T23:01:20.108195Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fcc5b887-e0e2-4a17-912a-fc68b7a8fbed · outbound

This paper cites H., Gonzalez, J.

MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design H., Gonzalez, J

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-15T23:01:20.111677Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9aa0f757-8182-4331-bd24-960600a3dd8e · outbound

This paper cites QuantMoE-Bench: Examining Post-Training Quantization for Mixture-of-Experts.

MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design QuantMoE-Bench: Examining Post-Training Quantization for Mixture-of-Experts

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-15T23:01:20.115100Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b0cd6e3-4513-46c0-9e10-5dd0c9b3bcb1 · outbound

This paper cites Awq: Activation-aware weight quantization for on-device llm compression and acceleration.

MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design Awq: Activation-aware weight quantization for on-device llm compression and acceleration

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:01:20.476199Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 82e02a0e-00ff-4469-a085-791b4132f00a · outbound

This paper cites QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving.

MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-15T23:01:20.121741Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8045fb33-47be-48ae-be19-9c8c422b18f5 · outbound

This paper cites DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model.

MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-15T23:01:20.125386Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c11c59ea-be45-44f3-ba3b-8b0c62cdea3c · outbound

This paper cites DeepSeek-V3 Technical Report.

MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design DeepSeek-V3 Technical Report

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-15T23:01:20.128688Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c216f39-8978-4db8-b4d6-5add35b02b26 · outbound

This paper cites KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache.

MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-15T23:01:20.131856Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5546954f-c393-4fed-baf4-296e1ba9c294 · outbound

This paper cites Pointer sentinel mixture models, 2016.

MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design Pointer sentinel mixture models, 2016

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-15T23:01:20.135454Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d406c120-e30f-4666-a268-cd6cdd663e32 · outbound

This paper cites OLMoE: Open Mixture-of-Experts Language Models.

MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design OLMoE: Open Mixture-of-Experts Language Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-15T23:01:20.138698Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc90ad85-5426-4828-a92f-99e0c69fa85e · outbound

This paper cites Massive Activations in Large Language Models.

MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design Massive Activations in Large Language Models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-15T23:01:20.142490Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40010b15-ec52-4f49-b234-e096bfb73003 · outbound

This paper cites HOBBIT: A Mixed Precision Expert Offloading System for Fast MoE Inference.

MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design HOBBIT: A Mixed Precision Expert Offloading System for Fast MoE Inference

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-15T23:01:20.145976Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94be0a7a-2c94-49e8-bf56-a42d2a7e4936 · outbound

This paper cites CUTLASS , January 2023.

MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design CUTLASS , January 2023

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-15T23:01:20.149211Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8077026f-2022-4705-8605-6602c0fb99bd · outbound

This paper cites Introducing DBRX: A New State-of-the-Art Open LLM , 2024.

MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design Introducing DBRX: A New State-of-the-Art Open LLM , 2024

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:01:20.453101Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 766fb9b8-4356-41e6-a632-aadb94f155d4 · outbound

This paper cites Haq: Hardware-aware automated quantization with mixed precision.

MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design Haq: Hardware-aware automated quantization with mixed precision

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:01:20.442414Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 7a091d6f-6b83-4fd1-8f30-a549748a27f1 · outbound

This paper cites Roofline: an insightful visual performance model for multicore architectures.

MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design Roofline: an insightful visual performance model for multicore architectures

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:01:20.431000Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation d898436a-7226-44cc-ae98-1d0efa43961d · outbound

This paper cites SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models.

MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-15T23:01:20.163033Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eddbd31d-f171-4b83-b690-17228831ae6f · outbound

This paper cites OpenMoE: An Early Effort on Open Mixture-of-Experts Language Models.

MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design OpenMoE: An Early Effort on Open Mixture-of-Experts Language Models

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-15T23:01:20.166912Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd7beb66-6f9b-40f3-a631-1496e62c40c7 · outbound

This paper cites Qwen2.5 Technical Report.

MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design Qwen2.5 Technical Report

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-15T23:01:20.170464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96252e40-ad26-42ad-b7a9-d50829ebd01a · outbound

This paper cites WKVQuant: Quantizing Weight and Key/Value Cache for Large Language Models Gains More.

MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design WKVQuant: Quantizing Weight and Key/Value Cache for Large Language Models Gains More

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-15T23:01:20.173955Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d7a95aa-ce8c-4afb-b10d-3c0656c2ece8 · outbound

This paper cites Atom: Low-bit quantization for efficient and accurate llm serving.

MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design Atom: Low-bit quantization for efficient and accurate llm serving

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-15T23:01:20.177528Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d12f9fc-d808-40e2-a996-746172485f14 · outbound

This paper cites Codegeex: A pre-trained model for code generation with multilingual benchmarking on humaneval-x.

MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design Codegeex: A pre-trained model for code generation with multilingual benchmarking on humaneval-x

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-15T23:01:20.181224Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation aac9bb44-f36d-488a-8da0-8cff6d5dd7b3 · inbound

Get Experience from Practice: LLM Agents with Record & Replay cites this paper.

Get Experience from Practice: LLM Agents with Record & Replay MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T14:44:23.206783Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e76c524-1d36-4d4b-b0e7-1723665d2ccc · inbound

MoE-Compression: How the Compression Error of Experts Affects the Inference Accuracy of MoE Model? cites this paper.

MoE-Compression: How the Compression Error of Experts Affects the Inference Accuracy of MoE Model? MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-04T21:51:03.992193Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f50dad6-e6cb-4bef-a7a2-38beaa5ceeba · inbound

LayerScope: Predictive Cross-Layer Scheduling for Efficient Multi-Batch MoE Inference on Legacy Servers cites this paper.

LayerScope: Predictive Cross-Layer Scheduling for Efficient Multi-Batch MoE Inference on Legacy Servers MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-18T12:41:22.798871Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation a1e71420-08dd-4415-bec4-d6d31c269da7 · inbound

PuzzleMoE: Efficient Compression of Large Mixture-of-Experts Models via Sparse Expert Merging and Bit-packed inference cites this paper.

PuzzleMoE: Efficient Compression of Large Mixture-of-Experts Models via Sparse Expert Merging and Bit-packed inference MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-03T23:41:52.850528Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1861e9f3-1d25-473e-916f-a8c08c0f001a · inbound

CoGR-MoE: Concept-Guided Expert Routing with Consistent Selection and Flexible Reasoning for Visual Question Answering cites this paper.

CoGR-MoE: Concept-Guided Expert Routing with Consistent Selection and Flexible Reasoning for Visual Question Answering MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-10T07:11:53.205305Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation abbf53c6-7b83-45a6-bc60-0514dfa14d96 · inbound

VisMMOE: Exploiting Visual-Expert Affinity for Efficient Visual-Language MoE Offloading cites this paper.

VisMMOE: Exploiting Visual-Expert Affinity for Efficient Visual-Language MoE Offloading MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-11T16:36:06.704030Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 4315bd31-77f7-43ef-971f-904869774e49 · inbound

GEMQ: Global Expert-Level Mixed-Precision Quantization for MoE LLMs cites this paper.

GEMQ: Global Expert-Level Mixed-Precision Quantization for MoE LLMs MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-25T05:36:39.963748Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation f994a790-dfd9-4824-a686-9f7f09ec4ad9 · inbound

AlphaQ: Calibration-Free Bit Allocation for Mixture-of-Experts Quantization cites this paper.

AlphaQ: Calibration-Free Bit Allocation for Mixture-of-Experts Quantization MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-07-02T07:06:44.793200Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.