MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference | Paper Citation Record

Observation b0389ef3-da40-46f6-b694-d9dd588926c7 · outbound

This paper cites Training DNNs with Hybrid Block Floating Point.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference Training DNNs with Hybrid Block Floating Point

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:27.151541Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e210193d-bab0-49e1-b61c-e1d60621ce0e · outbound

This paper cites Outlier Suppression+: Accurate quantization of large language models by equivalent and optimal shifting and scaling.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference Outlier Suppression+: Accurate quantization of large language models by equivalent and optimal shifting and scaling

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:27.226905Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ad65d40-01ba-469f-a601-1e9fa4083ded · outbound

This paper cites 2021 , eprint=.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference 2021 , eprint=

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:27.293408Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dee5b13f-7326-4bb9-a742-9a0e250b63b4 · outbound

This paper cites All Bark and No Bite: Rogue Dimensions in Transformer Language Models Obscure Representational Quality.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference All Bark and No Bite: Rogue Dimensions in Transformer Language Models Obscure Representational Quality

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:27.357886Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1bb3eca-1d65-4534-ab2a-c7672dd1587e · outbound

This paper cites Understanding and Overcoming the Challenges of Efficient Transformer Quantization.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference Understanding and Overcoming the Challenges of Efficient Transformer Quantization

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:27.428735Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ab90303-b202-492b-bdd9-e5f065d5e817 · outbound

This paper cites Advances in Neural Information Processing Systems , volume=.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference Advances in Neural Information Processing Systems , volume=

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:27.497511Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be13ca87-9323-40a3-bad4-990ba4de8185 · outbound

This paper cites Microscaling Data Formats for Deep Learning.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference Microscaling Data Formats for Deep Learning

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:27.562005Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09757515-49e5-465d-a2b6-4d90a40f9eea · outbound

This paper cites Proceedings of the 36th ACM International Conference on Supercomputing , pages=.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference Proceedings of the 36th ACM International Conference on Supercomputing , pages=

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:27.623831Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c164e073-01a3-4777-ab6f-479d2ada1105 · outbound

This paper cites Proceedings of the 52nd Annual International Symposium on Computer Architecture , pages=.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference Proceedings of the 52nd Annual International Symposium on Computer Architecture , pages=

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:27.685221Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca3d3686-578e-44f1-a518-051294a96911 · outbound

This paper cites MICRO-54: 54th Annual IEEE/ACM International Symposium on Microarchitecture , pages=.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference MICRO-54: 54th Annual IEEE/ACM International Symposium on Microarchitecture , pages=

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:27.746603Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea9fbdea-66b5-4ed5-893a-3c13ad9b828f · outbound

This paper cites Outliers Dimensions that Disrupt Transformers Are Driven by Frequency.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference Outliers Dimensions that Disrupt Transformers Are Driven by Frequency

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:27.817771Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81a639f2-4965-41dc-a50c-f5979d8c4a27 · outbound

This paper cites LUT-GEMM: Quantized Matrix Multiplication based on LUTs for Efficient Inference in Large-Scale Generative Language Models.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference LUT-GEMM: Quantized Matrix Multiplication based on LUTs for Efficient Inference in Large-Scale Generative Language Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:27.877147Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25b40a43-1701-4822-b146-c3fd2fdc511c · outbound

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

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference SqueezeLLM: Dense-and-Sparse Quantization

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:27.941291Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation baea74a0-fbe7-4d83-a4f2-5bd54d12bb5e · outbound

This paper cites LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:28.018798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60856a8d-2376-4ff0-ae21-e3b971402ee1 · outbound

This paper cites 2018 , eprint=.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference 2018 , eprint=

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:28.080747Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0f61271-4cc9-4183-9a57-8f0aa716cb7b · outbound

This paper cites 2019 , eprint=.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference 2019 , eprint=

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:28.165900Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d150366b-146d-4864-8500-6d7060c83dfc · outbound

This paper cites Microscaling Data Formats for Deep Learning.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference Microscaling Data Formats for Deep Learning

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:28.283144Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7eaa3de-7ed0-40dd-9210-432173e44e2a · outbound

This paper cites SparseGPT: Massive Language Models Can be Accurately Pruned in One-Shot , booktitle =.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference SparseGPT: Massive Language Models Can be Accurately Pruned in One-Shot , booktitle =

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:28.431686Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce162646-48aa-4be1-9ce6-a3778d250254 · outbound

This paper cites SpinQuant: LLM quantization with learned rotations.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference SpinQuant: LLM quantization with learned rotations

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:28.552379Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25996b48-6dd8-422b-96bc-e1f2fada2255 · outbound

This paper cites A Simple and Effective Pruning Approach for Large Language Models.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference A Simple and Effective Pruning Approach for Large Language Models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:28.673389Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e82efbf-98d6-4a66-9323-68cde424840e · outbound

This paper cites Accelerating Sparse Deep Neural Networks.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference Accelerating Sparse Deep Neural Networks

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:28.796302Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 966a36ac-594e-4460-85d5-7fc95c47b4af · outbound

This paper cites OPT: Open Pre-trained Transformer Language Models.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference OPT: Open Pre-trained Transformer Language Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:28.913039Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ce3fa1a-6ef3-410b-825c-6da4cac418d2 · outbound

This paper cites Proceedings of Machine Learning and Systems , volume=.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference Proceedings of Machine Learning and Systems , volume=

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:29.029903Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6dc16e26-a030-47d0-bc34-98fe85a0e521 · outbound

This paper cites Proceedings of the 50th Annual International Symposium on Computer Architecture , pages=.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference Proceedings of the 50th Annual International Symposium on Computer Architecture , pages=

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:29.203862Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ffd64e2b-1494-475b-af17-45feca4df541 · outbound

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

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models , booktitle =

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:29.352243Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e26c0881-9a2d-4871-9292-808ac00247b1 · outbound

This paper cites 5th International Conference on Learning Representations,.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference 5th International Conference on Learning Representations,

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:29.460631Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f333cd00-d380-48cd-bdc3-4a4424b391ee · outbound

This paper cites Proceedings of the IEEE conference on computer vision and pattern recognition , pages=.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference Proceedings of the IEEE conference on computer vision and pattern recognition , pages=

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:29.579510Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6804e4d-f97a-4505-bab9-91bb0299cfdf · outbound

This paper cites Wikimedia Downloads.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference Wikimedia Downloads

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:29.693882Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d3df61a-3d72-4515-a04f-de8cec42d0d2 · outbound

This paper cites The IEEE International Conference on Computer Vision (ICCV) , month =.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference The IEEE International Conference on Computer Vision (ICCV) , month =

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:29.834874Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c68e3a6b-6601-45e1-b8d1-b1c1da5fab5a · outbound

This paper cites 2009 IEEE conference on computer vision and pattern recognition , pages=.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference 2009 IEEE conference on computer vision and pattern recognition , pages=

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:29.960689Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6c9bd04-9fae-4297-887f-17543f335fa9 · outbound

This paper cites Gomez and Lukasz Kaiser and Illia Polosukhin , editor =.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference Gomez and Lukasz Kaiser and Illia Polosukhin , editor =

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:30.030535Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation def36568-02ca-476d-86f0-fb1192916241 · outbound

This paper cites Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies,.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies,

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:30.114261Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 644754d7-4896-4a11-8dce-b379667eeb6c · outbound

This paper cites 9th International Conference on Learning Representations,.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference 9th International Conference on Learning Representations,

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:30.203691Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 474a638d-3154-4452-a01e-77602f0cde8a · outbound

This paper cites 2019 , file =.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference 2019 , file =

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:30.285158Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a877c2d5-a1f7-4888-9baf-33308fbe9605 · outbound

This paper cites 2024 , eprint=.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference 2024 , eprint=

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:30.372935Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e7a4a44-a773-460e-928b-ad3ba0d012ae · outbound

This paper cites Mixed Precision Training.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference Mixed Precision Training

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:30.460917Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78f2d4e3-27db-43b5-96ff-c32b9f855a35 · outbound

This paper cites Chung and Zhaoxia (Summer) Deng and Sam Naghshineh and Jongsoo Park and Maxim Naumov , editor =.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference Chung and Zhaoxia (Summer) Deng and Sam Naghshineh and Jongsoo Park and Maxim Naumov , editor =

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:30.542653Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10c5b0b5-783b-4aaa-a46e-b81edeb8e1e0 · outbound

This paper cites Pushing the Limits of Narrow Precision Inferencing at Cloud Scale with Microsoft Floating Point , url =.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference Pushing the Limits of Narrow Precision Inferencing at Cloud Scale with Microsoft Floating Point , url =

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:30.653340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1f1a71c-be6a-43d8-89dc-7a4fdc419470 · outbound

This paper cites 2022 IEEE International Symposium on High-Performance Computer Architecture (HPCA) , pages=.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference 2022 IEEE International Symposium on High-Performance Computer Architecture (HPCA) , pages=

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:30.710712Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 29762dc7-fc3d-43a3-be61-016b011f42e6 · outbound

This paper cites FP8 Formats for Deep Learning.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference FP8 Formats for Deep Learning

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:30.799204Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42b3fb62-35de-4c9d-ab99-2c785ed18b7a · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:30.911126Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05fb1707-c374-4d69-884e-ca9c5228a565 · outbound

This paper cites 2024 , eprint=.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference 2024 , eprint=

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:30.991729Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 305d4f87-174e-49f1-b38d-6a611044d583 · outbound

This paper cites Proceedings of the AAAI conference on artificial intelligence , volume=.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference Proceedings of the AAAI conference on artificial intelligence , volume=

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:31.046211Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e1c64f7-e564-4713-ab81-3c9b78de1a97 · outbound

This paper cites ACM Transactions on Embedded Computing Systems (TECS) , volume=.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference ACM Transactions on Embedded Computing Systems (TECS) , volume=

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:31.128667Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8fe9537c-75da-4cbd-8d2b-47820e39d969 · outbound

This paper cites Advances in Neural Information Processing Systems , volume=.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference Advances in Neural Information Processing Systems , volume=

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:31.201090Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64484466-22d4-4f93-b236-c19aa6ff4dd0 · outbound

This paper cites ArXiv , year=.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference ArXiv , year=

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:31.262683Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1815c434-9e51-456b-a152-bd5f2a7291e7 · outbound

This paper cites International Conference on machine learning , pages=.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference International Conference on machine learning , pages=

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:31.291334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 797337d0-c682-466f-bdb8-ee247590fa9a · outbound

This paper cites Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:31.414720Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6424e814-38e0-4037-939a-c5b3d31e7335 · outbound

This paper cites Joint Pruning & Quantization for Extremely Sparse Neural Networks.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference Joint Pruning & Quantization for Extremely Sparse Neural Networks

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:31.547507Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 32dce6fb-050d-4af8-ad01-1edb704f03f4 · outbound

This paper cites Towards Optimal Compression: Joint Pruning and Quantization.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference Towards Optimal Compression: Joint Pruning and Quantization

Reference 50

Resolution: verified exact; local_arxiv, observed 2026-08-01T17:14:13.463510Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 8446f3c8-35a7-4497-9763-2116970a036d · outbound

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

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:31.870818Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7941fbd8-78b7-48a4-8d00-31924986a027 · outbound

This paper cites Deep Compression of Pre-trained Transformer Models , booktitle =.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference Deep Compression of Pre-trained Transformer Models , booktitle =

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:32.020992Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aba23c4a-96e7-4f66-b483-04d77f2d208b · outbound

This paper cites Training Deep Neural Networks with Joint Quantization and Pruning of Weights and Activations.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference Training Deep Neural Networks with Joint Quantization and Pruning of Weights and Activations

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:32.251422Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65dcef89-67da-49b8-99cc-08dedd0ad554 · outbound

This paper cites Frontiers in Artificial Intelligence , volume=.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference Frontiers in Artificial Intelligence , volume=

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:32.440054Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8c5b75c-c143-4f4f-981e-bf7e805fc667 · outbound

This paper cites International Conference on Machine Learning , pages=.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference International Conference on Machine Learning , pages=

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:32.631618Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95579736-d00c-4d24-92b0-f59d40975db7 · outbound

This paper cites Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:32.793626Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c751855a-07e2-4107-bd3d-766c41280517 · outbound

This paper cites Advances in neural information processing systems , volume=.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference Advances in neural information processing systems , volume=

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:32.906537Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0be79ddd-3208-48c3-a2a9-c320f0bd02c8 · outbound

This paper cites Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:33.043803Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5fed8344-2da6-4942-9f8c-b8a8c30f01b6 · outbound

This paper cites Advances in neural information processing systems , volume=.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference Advances in neural information processing systems , volume=

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:33.180569Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 47b0d489-c94f-45a7-955e-f63e5af53786 · outbound

This paper cites Advances in neural information processing systems , volume=.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference Advances in neural information processing systems , volume=

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:33.314659Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13597980-b2fc-4589-86e2-9cbe858d1848 · outbound

This paper cites Advances in neural information processing systems , volume=.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference Advances in neural information processing systems , volume=

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:33.442558Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 241dab0e-83f3-4a53-900d-5974b2afe19e · outbound

This paper cites IEEE international conference on neural networks , pages=.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference IEEE international conference on neural networks , pages=

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:33.514064Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ada5906c-7e26-4b42-85b2-b6f5fd44572a · outbound

This paper cites Advances in neural information processing systems , volume=.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference Advances in neural information processing systems , volume=

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:33.611359Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4da7d07-508c-4ae8-9598-85399e46d19d · outbound

This paper cites 2024 , eprint=.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference 2024 , eprint=

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:33.714207Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d797cb1-e33a-4b9f-96dc-1652136e8d05 · outbound

This paper cites The Optimal BERT Surgeon: Scalable and Accurate Second-Order Pruning for Large Language Models.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference The Optimal BERT Surgeon: Scalable and Accurate Second-Order Pruning for Large Language Models

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:33.850789Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8746ab1d-cedf-43d5-99ce-89b99cd35aa2 · outbound

This paper cites The Thirty-Third.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference The Thirty-Third

Reference 66

Resolution: verified exact; doi, observed 2026-08-01T17:14:13.147953Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 373a98bd-fdc6-4aaa-b8fa-48ec2557e0fd · outbound

This paper cites Accelerator-Aware Pruning for Convolutional Neural Networks , journal =.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference Accelerator-Aware Pruning for Convolutional Neural Networks , journal =

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:34.100741Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a810e8b-7652-4b8a-b392-75ac3fbafffb · outbound

This paper cites Channel Permutations for.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference Channel Permutations for

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:34.266577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 343f5256-7909-482b-9295-dd4d1bfa9e39 · outbound

This paper cites 9th International Conference on Learning Representations,.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference 9th International Conference on Learning Representations,

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:34.408624Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 745da703-9490-4c08-b19e-4464f14a3ac0 · outbound

This paper cites 2021 , URL =.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference 2021 , URL =

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:34.483305Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4300319b-01b1-4228-b901-88b0544c573f · outbound

This paper cites 2022 , URL =.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference 2022 , URL =

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:34.554232Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70e9241b-bc2c-49aa-9631-a3ed4689380b · outbound

This paper cites 2020 , URL =.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference 2020 , URL =

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:34.637548Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd403b5e-f19f-4d4a-b375-b4a06b601831 · outbound

This paper cites an unresolved cited work.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference Unresolved cited work

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:34.735064Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0e05e7b-dd3a-45d1-a6a1-b47c56e23fbe · outbound

This paper cites Accelerated Sparse Neural Training:.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference Accelerated Sparse Neural Training:

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:34.815551Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0aa4e79-4833-4aff-b50c-ded34aa84d66 · outbound

This paper cites International Conference on Machine Learning,.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference International Conference on Machine Learning,

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:34.917531Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 867f4a22-91d2-41b7-859e-50d858f61792 · outbound

This paper cites Accuracy Booster: Enabling 4-bit Fixed-point Arithmetic for DNN Training.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference Accuracy Booster: Enabling 4-bit Fixed-point Arithmetic for DNN Training

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:34.994910Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9560cc0-c5e4-4a2c-a9ac-65191242fae9 · outbound

This paper cites Proceedings of the 37th International Conference on Machine Learning , pages =.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference Proceedings of the 37th International Conference on Machine Learning , pages =

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:35.100065Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b85aa1d-4cae-4590-9534-acc867ec750c · outbound

This paper cites 2023 , eprint=.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference 2023 , eprint=

Reference 78

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:35.176718Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61014f32-1bc1-48f0-8eb1-7ab69133c344 · outbound

This paper cites Proceedings of Machine Learning and Systems , volume=.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference Proceedings of Machine Learning and Systems , volume=

Reference 79

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:35.291683Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 07bcc682-d597-4f52-b2f9-1927492a6882 · outbound

This paper cites Advances in neural information processing systems , volume=.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference Advances in neural information processing systems , volume=

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:35.375508Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 69adbd2e-2e04-4f3a-a401-c2f24fb86b1b · outbound

This paper cites Advances in Neural Information Processing Systems , volume=.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference Advances in Neural Information Processing Systems , volume=

Reference 81

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:35.476974Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e17c489-6900-4efc-816d-db83e14640d2 · outbound

This paper cites International Conference on Machine Learning , pages=.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference International Conference on Machine Learning , pages=

Reference 82

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:35.582690Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b58cbc9d-c761-451e-aa26-f54b78697daf · outbound

This paper cites Scaling Laws for Sparsely-Connected Foundation Models.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference Scaling Laws for Sparsely-Connected Foundation Models

Reference 83

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:35.695223Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98c21efa-e11d-4d5b-aa82-16d3e1bf8ecc · outbound

This paper cites Training Recipe for N:M Structured Sparsity with Decaying Pruning Mask.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference Training Recipe for N:M Structured Sparsity with Decaying Pruning Mask

Reference 84

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:35.769810Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ebd3c216-b495-4a92-bb44-6cd0934186f0 · outbound

This paper cites Dynamic Sparse Training with Structured Sparsity.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference Dynamic Sparse Training with Structured Sparsity

Reference 85

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:35.883139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7af72ee-4284-4e6a-81e0-01d3a8ee0427 · outbound

This paper cites Efficient Processing of Deep Neural Networks , series =.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference Efficient Processing of Deep Neural Networks , series =

Reference 86

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:35.977544Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab0625bd-c4f3-4105-b3b6-67e5e2ef27ef · outbound

This paper cites 7th International Conference on Learning Representations,.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference 7th International Conference on Learning Representations,

Reference 87

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:36.026630Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd48744e-1df3-435f-984b-5707532ed539 · outbound

This paper cites Intelligent Computing: Proceedings of the 2021 Computing Conference, Volume 3 , pages=.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference Intelligent Computing: Proceedings of the 2021 Computing Conference, Volume 3 , pages=

Reference 88

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:36.065756Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27dbc204-fc95-4273-8515-b26b13b2a05c · outbound

This paper cites Proceedings of the 37th International Conference on Machine Learning,.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference Proceedings of the 37th International Conference on Machine Learning,

Reference 89

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:36.119748Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02e80b84-3ca6-4e61-a0fd-1b9befb9d992 · outbound

This paper cites USM-Lite: Quantization and Sparsity Aware Fine-tuning for Speech Recognition with Universal Speech Models.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference USM-Lite: Quantization and Sparsity Aware Fine-tuning for Speech Recognition with Universal Speech Models

Reference 90

Resolution: metadata mismatch; local_arxiv, observed 2026-08-01T17:14:12.531140Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 0798e960-4843-403a-afec-510fafde30f7 · outbound

This paper cites Progressive Gradient Flow for Robust N:M Sparsity Training in Transformers.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference Progressive Gradient Flow for Robust N:M Sparsity Training in Transformers

Reference 91

Resolution: verified exact; local_arxiv, observed 2026-08-01T17:14:12.239179Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 8fb65693-9341-4d79-b5e9-98c056c4a409 · outbound

This paper cites Pixelated Butterfly: Simple and Efficient Sparse training for Neural Network Models , booktitle =.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference Pixelated Butterfly: Simple and Efficient Sparse training for Neural Network Models , booktitle =

Reference 92

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:36.476138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d56828e-22be-413d-8a7f-eeddc0f13cef · outbound

This paper cites Prune and Tune: Improving Efficient Pruning Techniques for Massive Language Models , booktitle =.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference Prune and Tune: Improving Efficient Pruning Techniques for Massive Language Models , booktitle =

Reference 93

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:36.636279Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2938dbe-005b-49dc-80d4-389d659c0a9c · outbound

This paper cites an unresolved cited work.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference Unresolved cited work

Reference 94

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:36.735369Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7cdbae7-6958-43f1-9bb5-4bc88e2f5aeb · outbound

This paper cites Mistral 7B.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference Mistral 7B

Reference 95

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:36.742446Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ee4cc51-b346-419c-9899-a56708e9e1ce · outbound

This paper cites BLOOM: A 176B-Parameter Open-Access Multilingual Language Model.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference BLOOM: A 176B-Parameter Open-Access Multilingual Language Model

Reference 96

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:36.861472Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46bde947-e50b-46bc-adf8-7158ecdea99a · outbound

This paper cites The Falcon Series of Open Language Models.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference The Falcon Series of Open Language Models

Reference 97

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:37.076833Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e3f08f2-4f8f-4a72-9a3e-13b8900b7457 · outbound

This paper cites Gemma: Open Models Based on Gemini Research and Technology.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference Gemma: Open Models Based on Gemini Research and Technology

Reference 98

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:37.200752Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d329632a-b6e8-47b3-8adb-85009046346e · outbound

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

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs

Reference 99

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:37.341730Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c28d77a2-3c32-42fd-8617-a38ec0732f0a · outbound

This paper cites GPT-4 Technical Report.

MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference GPT-4 Technical Report

Reference 100

Resolution: unresolved; no resolver link, observed 2026-08-01T17:12:37.492741Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers