% Verified by web lookup on 2026-11-01 (see research/prior_art.csv, column evidence_url_seen). % Each entry was checked on its arXiv/publisher/GitHub page by the literature sub-agent; re-verified during Gate G. @article{eliseev2023fast, title={Fast Inference of Mixture-of-Experts Language Models with Offloading}, author={Eliseev, Artyom and Mazur, Denis}, journal={arXiv preprint arXiv:2312.17238}, year={2023} } @article{xue2024moeinfinity, title={{MoE-Infinity}: Efficient {MoE} Inference on Personal Machines with Sparsity-Aware Expert Cache}, author={Xue, Leyang and Fu, Yao and Lu, Zhan and Mai, Luo and Marina, Mahesh}, journal={arXiv preprint arXiv:2401.14361}, year={2024} } @inproceedings{hwang2024pregated, title={Pre-gated {MoE}: An Algorithm-System Co-Design for Fast and Scalable Mixture-of-Expert Inference}, author={Hwang, Ranggi and Wei, Jianyu and Cao, Shijie and Hwang, Changho and Tang, Xiaohu and Cao, Ting and Yang, Mao}, booktitle={Proceedings of the 51st ACM/IEEE Annual International Symposium on Computer Architecture (ISCA)}, year={2024}, note={arXiv:2308.12066} } @article{yi2025edgemoe, title={{EdgeMoE}: Empowering Sparse Large Language Models on Mobile Devices}, author={Yi, Rongjie and Guo, Liwei and Wei, Shiyun and Zhou, Ao and Wang, Shangguang and Xu, Mengwei}, journal={IEEE Transactions on Mobile Computing}, volume={24}, number={8}, pages={7059--7073}, year={2025}, doi={10.1109/TMC.2025.3546466}, note={arXiv:2308.14352} } @article{zhong2024adapmoe, title={{AdapMoE}: Adaptive Sensitivity-based Expert Gating and Management for Efficient {MoE} Inference}, author={Zhong, Shuzhang and Liang, Ling and Wang, Yuan and Wang, Runsheng and Huang, Ru and Li, Meng}, journal={arXiv preprint arXiv:2408.10284}, year={2024}, note={Related DOI 10.1145/3676536.3676741 (ICCAD 2024, not verified on ACM page)} } @article{tang2024hobbit, title={{HOBBIT}: A Mixed Precision Expert Offloading System for Fast {MoE} Inference}, author={Tang, Peng and Liu, Jiacheng and Hou, Xiaofeng and Pu, Yifei and Wang, Jing and Heng, Pheng-Ann and Li, Chao and Guo, Minyi}, journal={arXiv preprint arXiv:2411.01433}, year={2024} } @inproceedings{kamahori2025fiddler, title={Fiddler: {CPU-GPU} Orchestration for Fast Inference of Mixture-of-Experts Models}, author={Kamahori, Keisuke and Tang, Tian and Gu, Yile and Zhu, Kan and Kasikci, Baris}, booktitle={International Conference on Learning Representations (ICLR)}, year={2025}, note={arXiv:2402.07033} } @inproceedings{cao2025moelightning, title={{MoE-Lightning}: High-Throughput {MoE} Inference on Memory-constrained {GPUs}}, author={Cao, Shiyi and Liu, Shu and Griggs, Tyler and Schafhalter, Peter and Liu, Xiaoxuan and Sheng, Ying and Gonzalez, Joseph E. and Zaharia, Matei and Stoica, Ion}, booktitle={Proceedings of the 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS)}, year={2025}, note={arXiv:2411.11217; ACM DOI not retrieved} } @inproceedings{du2024sida, title={{SiDA-MoE}: Sparsity-Inspired Data-Aware Serving for Efficient and Scalable Large Mixture-of-Experts Models}, author={Du, Zhixu and Li, Shiyu and Wu, Yuhao and Jiang, Xiangyu and Sun, Jingwei and Zheng, Qilin and Wu, Yongkai and Li, Ang and Li, Hai and Chen, Yiran}, booktitle={Proceedings of Machine Learning and Systems (MLSys)}, year={2024}, note={arXiv:2310.18859} } @article{song2024promoe, title={{ProMoE}: Fast {MoE}-based {LLM} Serving using Proactive Caching}, author={Song, Xiaoniu and Zhong, Zihang and Chen, Rong and Chen, Haibo}, journal={arXiv preprint arXiv:2410.22134}, year={2024} } @inproceedings{he2026expertflow, title={{ExpertFlow}: Efficient Mixture-of-Experts Inference via Predictive Expert Caching and Token Scheduling}, author={He, Xin and Zhang, Shunkang and Tang, Kaijie and Shi, Shaohuai and Wang, Yuxin and Zeng, Zihao and Tang, Zhenheng and Chu, Xiaowen and Yin, Haiyan and Tsang, Ivor W. and Ong, Yew Soon}, booktitle={Proceedings of the Design Automation Conference (DAC)}, year={2026}, note={arXiv:2410.17954} } @article{yu2025finemoe, title={Taming Latency-Memory Trade-Off in {MoE}-Based {LLM} Serving via Fine-Grained Expert Offloading}, author={Yu, Hanfei and Cui, Xingqi and Zhang, Hong and Wang, Hao and Wang, Hao}, journal={arXiv preprint arXiv:2502.05370}, year={2025} } @inproceedings{zhang2025daop, title={{DAOP}: Data-Aware Offloading and Predictive Pre-Calculation for Efficient {MoE} Inference}, author={Zhang, Yujie and Aggarwal, Shivam and Mitra, Tulika}, booktitle={Design, Automation \& Test in Europe Conference (DATE)}, year={2025}, note={arXiv:2501.10375} } @article{xu2025moegen, title={{MoE-Gen}: High-Throughput {MoE} Inference on a Single {GPU} with Module-Based Batching}, author={Xu, Tairan and Xue, Leyang and Lu, Zhan and Jackson, Adrian and Mai, Luo}, journal={arXiv preprint arXiv:2503.09716}, year={2025} } @article{fang2025klotski, title={Klotski: Efficient Mixture-of-Expert Inference via Expert-Aware Multi-Batch Pipeline}, author={Fang, Zhiyuan and Huang, Yuegui and Hong, Zicong and Lyu, Yufeng and Chen, Wuhui and Yu, Yue and Yu, Fan and Zheng, Zibin}, journal={arXiv preprint arXiv:2502.06888}, year={2025} } @article{tairin2025emoe, title={{eMoE}: Task-aware Memory Efficient Mixture-of-Experts-Based ({MoE}) Model Inference}, author={Tairin, Suraiya and Mahmud, Shohaib and Shen, Haiying and Iyer, Anand}, journal={arXiv preprint arXiv:2503.06823}, year={2025} } @inproceedings{suo2025coserve, title={{CoServe}: Efficient Collaboration-of-Experts ({CoE}) Model Inference with Limited Memory}, author={Suo, Jiashun and Liao, Xiaojian and Xiao, Limin and Ruan, Li and Wang, Jinquan and Su, Xiao and Huo, Zhisheng}, booktitle={Proceedings of the 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS)}, year={2025}, note={arXiv:2503.02354} } @article{skliar2025cacheaware, title={Mixture of Cache-Conditional Experts for Efficient Mobile Device Inference}, author={Skliar, Andrii and van Rozendaal, Ties and Lepert, Romain and Boinovski, Todor and van Baalen, Mart and Nagel, Markus and Whatmough, Paul and Ehteshami Bejnordi, Babak}, journal={Transactions on Machine Learning Research}, year={2025}, note={arXiv:2412.00099} } @inproceedings{alizadeh2024flash, title={{LLM} in a flash: Efficient Large Language Model Inference with Limited Memory}, author={Alizadeh, Keivan and Mirzadeh, Iman and Belenko, Dmitry and Khatamifard, Karen and Cho, Minsik and Del Mundo, Carlo C and Rastegari, Mohammad and Farajtabar, Mehrdad}, booktitle={Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (ACL)}, year={2024}, note={arXiv:2312.11514} } @inproceedings{song2024powerinfer, title={{PowerInfer}: Fast Large Language Model Serving with a Consumer-grade {GPU}}, author={Song, Yixin and Mi, Zeyu and Xie, Haotong and Chen, Haibo}, booktitle={Proceedings of the ACM SIGOPS 30th Symposium on Operating Systems Principles (SOSP)}, year={2024}, note={arXiv:2312.12456} } @article{huang2023towards, title={Towards {MoE} Deployment: Mitigating Inefficiencies in Mixture-of-Expert ({MoE}) Inference}, author={Huang, Haiyang and Ardalani, Newsha and Sun, Anna and Ke, Liu and Lee, Hsien-Hsin S. and Sridhar, Anjali and Bhosale, Shruti and Wu, Carole-Jean and Lee, Benjamin}, journal={arXiv preprint arXiv:2303.06182}, year={2023} } @inproceedings{cai2024readme, title={{Read-ME}: Refactorizing {LLMs} as Router-Decoupled Mixture of Experts with System Co-Design}, author={Cai, Ruisi and Ro, Yeonju and Kim, Geon-Woo and Wang, Peihao and Ehteshami Bejnordi, Babak and Akella, Aditya and Wang, Zhangyang}, booktitle={Advances in Neural Information Processing Systems (NeurIPS)}, year={2024}, note={arXiv:2410.19123} } @article{yao2024exflow, title={Exploiting Inter-Layer Expert Affinity for Accelerating Mixture-of-Experts Model Inference}, author={Yao, Jinghan and Anthony, Quentin and Shafi, Aamir and Subramoni, Hari and Panda, Dhabaleswar K.}, journal={arXiv preprint arXiv:2401.08383}, year={2024} } @article{fang2025fate, title={Fate: Fast Edge Inference of Mixture-of-Experts Models via Cross-Layer Gate}, author={Fang, Zhiyuan and Hong, Zicong and Huang, Yuegui and Lyu, Yufeng and Chen, Wuhui and Yu, Yue and Yu, Fan and Zheng, Zibin}, journal={arXiv preprint arXiv:2502.12224}, year={2025} } @inproceedings{liang2026notall, title={Not All Models Suit Expert Offloading: On Local Routing Consistency of Mixture-of-Expert Models}, author={Liang, Jingcong and Wang, Siyuan and Tian, Miren and Li, Yitong and Tang, Duyu and Wei, Zhongyu}, booktitle={International Conference on Learning Representations (ICLR)}, year={2026}, note={arXiv:2505.16056} } @inproceedings{zhong2025hybrimoe, title={{HybriMoE}: Hybrid {CPU-GPU} Scheduling and Cache Management for Efficient {MoE} Inference}, author={Zhong, Shuzhang and Sun, Yanfan and Liang, Ling and Wang, Runsheng and Huang, Ru and Li, Meng}, booktitle={Proceedings of the Design Automation Conference (DAC)}, year={2025}, note={arXiv:2504.05897} } @inproceedings{huang2026cpugpu, title={Efficient {CPU-GPU} Collaborative Inference for {MoE}-based {LLMs} on Memory-Limited Systems}, author={Huang, En-Ming and Lin, Li-Shang and Lee, Chun-Yi}, booktitle={Asia and South Pacific Design Automation Conference (ASP-DAC)}, year={2026}, note={arXiv:2512.16473} } @inproceedings{zhao2026mobile, title={{MoBiLE}: Efficient Mixture-of-Experts Inference on Consumer {GPU} with Mixture of Big Little Experts}, author={Zhao, Yushu and Qin, Yubin and Wang, Yang and Yang, Xiaolong and Han, Huiming and Wei, Shaojun and Hu, Yang and Yin, Shouyi}, booktitle={Asia and South Pacific Design Automation Conference (ASP-DAC)}, year={2026}, note={arXiv:2510.12357} } @inproceedings{yu2026layerscope, title={{LayerScope}: Predictive Cross-Layer Scheduling for Efficient Multi-Batch {MoE} Inference on Legacy Servers}, author={Yu, Enda and Dong, Dezun and Zhang, Zhaoning and Bai, Zhe and Yang, Weiling and Wang, Haojie and Li, Dongsheng and Wu, Yongwei and Liao, Xiangke}, booktitle={Proceedings of the International Conference on Supercomputing (ICS)}, year={2026}, note={arXiv:2509.23638} } @article{shen2025expertflow, title={{ExpertFlow}: Adaptive Expert Scheduling and Memory Coordination for Efficient {MoE} Inference}, author={Shen, Zixu and Chu, Kexin and Zhang, Yifan and Xiang, Dawei and Wu, Runxin and Zhang, Wei}, journal={arXiv preprint arXiv:2510.26730}, year={2025} } @article{zhang2025duoserve, title={{DuoServe-MoE}: Dual-Phase Expert Prefetch and Caching for {LLM} Inference {QoS} Assurance}, author={Zhang, Yuning and Pinkert, Grant and Yang, Nan and Li, Yanli and Yuan, Dong}, journal={arXiv preprint arXiv:2509.07379}, year={2025} } @article{kim2026flashmoe, title={{FlashMoE}: Reducing {SSD} {I/O} Bottlenecks via {ML}-Based Cache Replacement for Mixture-of-Experts Inference on Edge Devices}, author={Kim, Byeongju and Lee, Jungwan and Han, Donghyeon and Yoo, Hoi-Jun and Kim, Sangyeob}, journal={arXiv preprint arXiv:2601.17063}, year={2026} } @inproceedings{pan2026trimoe, title={{TriMoE}: Augmenting {GPU} with {AMX}-Enabled {CPU} and {DIMM-NDP} for High-Throughput {MoE} Inference via Offloading}, author={Pan, Yudong and He, Yintao and Han, Tianhua and Liu, Lian and Zhao, Shixin and Chen, Zhirong and Wang, Mengdi and Li, Cangyuan and Han, Yinhe and Wang, Ying}, booktitle={Proceedings of the Design Automation Conference (DAC)}, year={2026}, note={arXiv:2603.01058} } @article{kong2026specprefetch, title={{SpecPrefetch}: Parameter-Efficient Expert Prefetching for Sparse {MoE} Foundation Models}, author={Kong, Jinwei and Meng, Runqi and Wang, Fanyi and Qiu, Wentao and Hu, Haotian and Zhou, Yongjian and Ge, Zhenhua}, journal={arXiv preprint arXiv:2607.24787}, year={2026} } @article{wang2026seqmoe, title={{SeqMoE}: Toward Full-Load Performance via Predictive and Graph-Compatible {MoE} Offloading}, author={Wang, Zihan and Wang, Yuqi and Gong, Lei and Tang, Cheng and Lou, Wenqi and Wang, Teng and Wang, Chao and Zhou, Xuehai}, journal={arXiv preprint arXiv:2609.12978}, year={2026} } @article{liang2026ssdllama, title={{SSD-LLaMA}: {SSD}-Native Inference for Trillion-Parameter {MoE} at 1+ Token/s on a Consumer {PC}}, author={Liang, Fangzhou and Shen, Yibin and Hu, Jianmin and Xu, Jiayang and Gao, Hanchi and Xu, Minxian and Meng, Zili}, journal={arXiv preprint arXiv:2609.18110}, year={2026} } @article{yang2026moecore, title={{MoE-CORE}: Coordinated Expert Offloading and Residency for Memory-Constrained {MoE} Inference}, author={Yang, Ke and Gao, Yongji and Li, Xushi and Luo, Kui and Zhang, Sicheng and Zhou, Tianming and Liu, Keyi and Lu, Shufang and Chen, Aoxuan and Meng, Jie and Gao, Jingchun and Li, Dan and You, Xinkai and Xia, Zhixiang and Shi, Yan and Liu, Yang and Zeng, Yanjia and Feng, Liangjun}, journal={arXiv preprint arXiv:2610.01950}, year={2026} } @article{yuan2026ordermoe, title={{OrderMoE}: An expert similarity driven distributed edge {MoE} inference}, author={Yuan, Xin and Li, Ning and Chen, Quan and Xu, Wenchao and Guo, Song}, journal={arXiv preprint arXiv:2607.17154}, year={2026} } @article{benazir2026npumoe, title={Efficient Mixture-of-Experts {LLM} Inference with {Apple Silicon} {NPUs}}, author={Benazir, Afsara and Lin, Felix Xiaozhu}, journal={arXiv preprint arXiv:2604.18788}, year={2026} } @article{alfarizy2026doesmoe, title={Does Mixture-of-Experts Actually Help Inference on Consumer and Edge Hardware? An Empirical Study}, author={Alfarizy, Alfarizy and Nguyen, Hung Truong Thanh and Richard, Ren{\'e} and Razavi-Far, Roozbeh and Cao, Hung}, journal={arXiv preprint arXiv:2606.21428}, year={2026} } @inproceedings{kannan2026greenbench, title={{GreenBench}: Benchmarking Energy Efficiency and Carbon Footprint of Open-Source {LLM} Inference on {Apple Silicon}}, author={Kannan, Rajeswari and Firke, Raj and Bengle, Shreya and Deshmukh, Srushti}, booktitle={IEEE International Conference on Computing, Communication, Control and Automation (ICCUBEA)}, year={2026}, note={arXiv:2608.28667} } @article{javat2026siliconshowdown, title={Silicon Showdown: Performance, Efficiency, and Ecosystem Barriers in Consumer-Grade {LLM} Inference}, author={Javat, Abdurrahman and Kazakov, Allan}, journal={arXiv preprint arXiv:2605.00519}, year={2026} } @article{rajesh2025productiongrade, title={Production-Grade Local {LLM} Inference on {Apple Silicon}: A Comparative Study of {MLX}, {MLC-LLM}, {Ollama}, {llama.cpp}, and {PyTorch MPS}}, author={Rajesh, Varun and Jodhpurkar, Om and Anbuselvan, Pooja and Singh, Mantinder and Jallepali, Ashok and Godbole, Shantanu and Sharma, Pradeep Kumar and Shrivastava, Hritvik}, journal={arXiv preprint arXiv:2511.05502}, year={2025} } @article{rathnayaka2026basert, title={{BaseRT}: Best-in-Class {LLM} Inference on {Apple Silicon} via Native {Metal}}, author={Rathnayaka, Prabod and Waschkowski, Fabian and Wesemann, Lukas}, journal={arXiv preprint arXiv:2607.00501}, year={2026} } @article{wilkins2024hybrid, title={Hybrid Heterogeneous Clusters Can Lower the Energy Consumption of {LLM} Inference Workloads}, author={Wilkins, Grant and Keshav, Srinivasan and Mortier, Richard}, journal={arXiv preprint arXiv:2407.00010}, year={2024} } @inproceedings{borzunov2023petals, title={Petals: Collaborative Inference and Fine-tuning of Large Models}, author={Borzunov, Alexander and Baranchuk, Dmitry and Dettmers, Tim and Riabinin, Maksim and Belkada, Younes and Chumachenko, Artem and Samygin, Pavel and Raffel, Colin}, booktitle={Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)}, pages={558--568}, year={2023}, doi={10.18653/v1/2023.acl-demo.54} } @article{li2025primacpp, title={{Prima.cpp}: Fast 30-70B {LLM} Inference on Heterogeneous and Low-Resource Home Clusters}, author={Li, Zonghang and Li, Tao and Feng, Wenjiao and Xiao, Rongxing and She, Jianshu and Huang, Hong and Guizani, Mohsen and Yu, Hongfang and Ho, Qirong and Xiang, Wei and Liu, Xue}, journal={arXiv preprint arXiv:2504.08791}, year={2025} } @misc{exo2025, title={exo: Run frontier {AI} locally}, author={{exo labs}}, howpublished={\url{https://github.com/exo-explore/exo}}, year={2025}, note={Accessed 2026-11-01} } @misc{llamacpp2026, title={llama.cpp: {LLM} inference in {C/C++}}, author={Gerganov, Georgi and {ggml-org contributors}}, howpublished={\url{https://github.com/ggml-org/llama.cpp}}, year={2026}, note={Accessed 2026-11-01; RPC backend documented at tools/rpc/README.md} } @misc{hannun2023mlx, title={{MLX}: Efficient and flexible machine learning on {Apple silicon}}, author={Hannun, Awni and Digani, Jagrit and Katharopoulos, Angelos and Collobert, Ronan}, howpublished={\url{https://github.com/ml-explore/mlx}}, year={2023}, note={Accessed 2026-11-01; distributed docs: \url{https://ml-explore.github.io/mlx/build/html/usage/distributed.html}} } @misc{apple2026mlxdistributed, title={Local and Distributed Large {LLM} Inference with {MLX} and {RDMA} on {Mac Studio}}, author={{Apple Machine Learning Research}}, howpublished={\url{https://machinelearning.apple.com/research/mlx-distributed-inference}}, year={2026}, note={Published 2026-10-15. Accessed 2026-11-01} } @misc{apple2026wwdc233, title={Explore distributed inference and training with {MLX} ({WWDC26} session 233)}, author={{Apple Inc.}}, howpublished={\url{https://developer.apple.com/videos/play/wwdc2026/233/}}, year={2026}, note={Accessed 2026-11-01} } @misc{geerling2025rdma, title={1.5 {TB} of {VRAM} on {Mac Studio} -- {RDMA} over {Thunderbolt 5}}, author={Geerling, Jeff}, howpublished={\url{https://jeffgeerling.com/blog/2025/15-tb-vram-on-mac-studio-rdma-over-thunderbolt-5}}, year={2025}, note={Blog post, 2025-12-18. Accessed 2026-11-01} } @inproceedings{rajbhandari2022deepspeedmoe, title={{DeepSpeed-MoE}: Advancing Mixture-of-Experts Inference and Training to Power Next-Generation {AI} Scale}, author={Rajbhandari, Samyam and Li, Conglong and Yao, Zhewei and Zhang, Minjia and Aminabadi, Reza Yazdani and Awan, Ammar Ahmad and Rasley, Jeff and He, Yuxiong}, booktitle={Proceedings of the 39th International Conference on Machine Learning (ICML)}, year={2022}, note={arXiv:2201.05596} } @misc{deepep2025, title={{DeepEP}: an efficient expert-parallel communication library}, author={Zhao, Chenggang and others}, howpublished={\url{https://github.com/deepseek-ai/DeepEP}}, year={2025}, note={Accessed 2026-11-01; author list abbreviated from the repository's own BibTeX} } @inproceedings{li2023lina, title={Accelerating Distributed {MoE} Training and Inference with {Lina}}, author={Li, Jiamin and Jiang, Yimin and Zhu, Yibo and Wang, Cong and Xu, Hong}, booktitle={Proceedings of the USENIX Annual Technical Conference (USENIX ATC)}, pages={945--959}, year={2023}, note={arXiv:2210.17223} } @article{hwang2023tutel, title={Tutel: Adaptive Mixture-of-Experts at Scale}, author={Hwang, Changho and Cui, Wei and Xiong, Yifan and Yang, Ziyue and Liu, Ze and Hu, Han and Wang, Zilong and Salas, Rafael and Jose, Jithin and Ram, Prabhat and Chau, Joe and Cheng, Peng and Yang, Fan and Yang, Mao and Xiong, Yongqiang}, journal={arXiv preprint arXiv:2206.03382}, year={2023}, note={Venue (MLSys 2023) not shown on arXiv page; unverified} } @article{gale2023megablocks, title={{MegaBlocks}: Efficient Sparse Training with Mixture-of-Experts}, author={Gale, Trevor and Narayanan, Deepak and Young, Cliff and Zaharia, Matei}, journal={arXiv preprint arXiv:2211.15841}, year={2023}, note={Venue (MLSys 2023) not shown on arXiv page; unverified} } @misc{colibri2026, title={colibri: Tiny engine, immense model}, author={Fornaro, Vincenzo}, howpublished={\url{https://github.com/JustVugg/colibri}}, year={2026}, note={Version 2.1.0, Apache-2.0. Accessed 2026-11-01. No paper or citation provided by the project} } % --- added 2026-11-01, verified on arxiv.org/abs pages (title, first authors, date) --- @article{muennighoff2024olmoe, title = {{OLMoE}: Open Mixture-of-Experts Language Models}, author = {Muennighoff, Niklas and Soldaini, Luca and Groeneveld, Dirk and Lo, Kyle and Morrison, Jacob and Min, Sewon and Shi, Weijia and Walsh, Pete and Tafjord, Oyvind and Lambert, Nathan and Gu, Yuling and Arora, Shane and Bhagia, Akshita and Schwenk, Dustin and Wadden, David and Wettig, Alexander and Hui, Binyuan and Dettmers, Tim and Kiela, Douwe and Farhadi, Ali and Smith, Noah A. and Koh, Pang Wei and Singh, Amanpreet and Hajishirzi, Hannaneh}, journal = {arXiv preprint arXiv:2409.02060}, year = {2024} } @article{yang2025qwen3, title = {Qwen3 Technical Report}, author = {Yang, An and Li, Anfeng and Yang, Baosong and others}, journal = {arXiv preprint arXiv:2505.09388}, year = {2025} }