{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T15:23:43Z","timestamp":1783610623953,"version":"3.55.0"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,16]],"date-time":"2024-12-16T00:00:00Z","timestamp":1734307200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,16]],"date-time":"2024-12-16T00:00:00Z","timestamp":1734307200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,12,16]]},"DOI":"10.1109\/icrc64395.2024.10937027","type":"proceedings-article","created":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T03:23:48Z","timestamp":1743132228000},"page":"1-6","source":"Crossref","is-referenced-by-count":11,"title":["Mixture of Experts with Mixture of Precisions for Tuning Quality of Service"],"prefix":"10.1109","author":[{"given":"HamidReza","family":"Imani","sequence":"first","affiliation":[{"name":"The George Washington University,Department of Electrical and Computer Engineering,Washington, D.C.,20052"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abdolah","family":"Amirany","sequence":"additional","affiliation":[{"name":"The George Washington University,Department of Electrical and Computer Engineering,Washington, D.C.,20052"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tarek","family":"El-Ghazawi","sequence":"additional","affiliation":[{"name":"The George Washington University,Department of Electrical and Computer Engineering,Washington, D.C.,20052"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.1.79"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1994.6.2.181"},{"key":"ref3","article-title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer","author":"Shazeer","year":"2017"},{"key":"ref4","first-page":"31","article-title":"Mesh-tensorflow: Deep learning for supercomputers","author":"Shazeer","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref5","article-title":"Fast inference of mixture-of-experts language models with offloading","author":"Eliseev","year":"2023"},{"key":"ref6","article-title":"Qmoe: Practical sub-1-bit compression of trillion-parameter models","author":"Frantar","year":"2023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.sustainlp-1.6"},{"key":"ref8","article-title":"Mixture of quantized experts (moqe): Complementary effect of low-bit quantization and robustness","author":"Kim","year":"2023"},{"key":"ref9","article-title":"Moe-infinity: Activation-aware expert offloading for efficient moe serving","author":"Xue","year":"2024"},{"key":"ref10","article-title":"Mixtral of experts","author":"Jiang","year":"2024"},{"issue":"120","key":"ref11","first-page":"1","article-title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity","volume":"23","author":"Fedus","year":"2022","journal-title":"Journal of Machine Learning Research"},{"key":"ref12","first-page":"5547","article-title":"Glam: Efficient scaling of language models with mixture-of-experts","volume-title":"International Conference on Machine Learning","author":"Du"},{"key":"ref13","article-title":"Scalable and efficient moe training for multitask multilingual models","author":"Kim","year":"2021"},{"key":"ref14","article-title":"Taming sparsely activated transformer with stochastic experts","author":"Zuo","year":"2021"},{"key":"ref15","article-title":"M6-10t: A sharing-delinking paradigm for efficient multi-trillion parameter pretraining","author":"Lin","year":"2021"},{"key":"ref16","first-page":"18332","article-title":"Deepspeed-moe: Advancing mixture-of-experts inference and training to power next-generation ai scale","volume-title":"International conference on machine learning","author":"Rajbhandari"},{"key":"ref17","article-title":"Sparse backpropagation for moe training","author":"Liu","year":"2023"},{"key":"ref18","first-page":"31094","article-title":"Flexgen: High-throughput generative inference of large language models with a single gpu","volume-title":"International Conference on Machine Learning","author":"Sheng"},{"key":"ref19","article-title":"Fiddler: Cpu-gpu orchestration for fast inference of mixture-of-experts models","author":"Kamahori","year":"2024"},{"key":"ref20","article-title":"Llm-qat: Data-free quantization aware training for large language models","author":"Liu","year":"2023"},{"key":"ref21","first-page":"36","article-title":"Qlora: Efficient finetuning of quantized llms","author":"Dettmers","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref22","article-title":"Awq: Activation-aware weight quantization for llm compression and acceleration","author":"Lin","year":"2023"},{"key":"ref23","first-page":"38087","article-title":"Smoothquant: Accurate and efficient post-training quantization for large language models","volume-title":"International Conference on Machine Learning","author":"Xiao"},{"key":"ref24","article-title":"Billm: Pushing the limit of post-training quantization for llms","author":"Huang","year":"2024"},{"key":"ref25","first-page":"7750","article-title":"The case for 4-bit precision: k-bit inference scaling laws","volume-title":"International Conference on Machine Learning","author":"Dettmers"},{"key":"ref26","article-title":"Demystifying the compression of mixture-of-experts through a unified framework","author":"He","year":"2024"},{"key":"ref27","first-page":"32","article-title":"Pytorch: An imperative style, high-performance deep learning library","author":"Paszke","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref28","article-title":"Huggingface\u2019s transformers: State-of-the-art natural language processing","author":"Wolf","year":"2019"},{"key":"ref29","article-title":"Pointer sentinel mixture models","author":"Merity","year":"2016"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.3115\/1075812.1075835"},{"issue":"140","key":"ref31","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"Journal of machine learning research"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2019.2940943"}],"event":{"name":"2024 IEEE International Conference on Rebooting Computing (ICRC)","location":"San Diego, CA, USA","start":{"date-parts":[[2024,12,16]]},"end":{"date-parts":[[2024,12,17]]}},"container-title":["2024 IEEE International Conference on Rebooting Computing (ICRC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10936635\/10936996\/10937027.pdf?arnumber=10937027","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,29]],"date-time":"2025-03-29T03:08:58Z","timestamp":1743217738000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10937027\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,16]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icrc64395.2024.10937027","relation":{},"subject":[],"published":{"date-parts":[[2024,12,16]]}}}