1% Verified by web lookup on 2026-11-01 (see research/prior_art.csv, column evidence_url_seen).2% Each entry was checked on its arXiv/publisher/GitHub page by the literature sub-agent; re-verified during Gate G.34@article{eliseev2023fast,5 title={Fast Inference of Mixture-of-Experts Language Models with Offloading},6 author={Eliseev, Artyom and Mazur, Denis},7 journal={arXiv preprint arXiv:2312.17238},8 year={2023}9}10@article{xue2024moeinfinity,11 title={{MoE-Infinity}: Efficient {MoE} Inference on Personal Machines with Sparsity-Aware Expert Cache},12 author={Xue, Leyang and Fu, Yao and Lu, Zhan and Mai, Luo and Marina, Mahesh},13 journal={arXiv preprint arXiv:2401.14361},14 year={2024}15}16@inproceedings{hwang2024pregated,17 title={Pre-gated {MoE}: An Algorithm-System Co-Design for Fast and Scalable Mixture-of-Expert Inference},18 author={Hwang, Ranggi and Wei, Jianyu and Cao, Shijie and Hwang, Changho and Tang, Xiaohu and Cao, Ting and Yang, Mao},19 booktitle={Proceedings of the 51st ACM/IEEE Annual International Symposium on Computer Architecture (ISCA)},20 year={2024},21 note={arXiv:2308.12066}22}23@article{yi2025edgemoe,24 title={{EdgeMoE}: Empowering Sparse Large Language Models on Mobile Devices},25 author={Yi, Rongjie and Guo, Liwei and Wei, Shiyun and Zhou, Ao and Wang, Shangguang and Xu, Mengwei},26 journal={IEEE Transactions on Mobile Computing},27 volume={24},28 number={8},29 pages={7059--7073},30 year={2025},31 doi={10.1109/TMC.2025.3546466},32 note={arXiv:2308.14352}33}34@article{zhong2024adapmoe,35 title={{AdapMoE}: Adaptive Sensitivity-based Expert Gating and Management for Efficient {MoE} Inference},36 author={Zhong, Shuzhang and Liang, Ling and Wang, Yuan and Wang, Runsheng and Huang, Ru and Li, Meng},37 journal={arXiv preprint arXiv:2408.10284},38 year={2024},39 note={Related DOI 10.1145/3676536.3676741 (ICCAD 2024, not verified on ACM page)}40}41@article{tang2024hobbit,42 title={{HOBBIT}: A Mixed Precision Expert Offloading System for Fast {MoE} Inference},43 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},44 journal={arXiv preprint arXiv:2411.01433},45 year={2024}46}47@inproceedings{kamahori2025fiddler,48 title={Fiddler: {CPU-GPU} Orchestration for Fast Inference of Mixture-of-Experts Models},49 author={Kamahori, Keisuke and Tang, Tian and Gu, Yile and Zhu, Kan and Kasikci, Baris},50 booktitle={International Conference on Learning Representations (ICLR)},51 year={2025},52 note={arXiv:2402.07033}53}54@inproceedings{cao2025moelightning,55 title={{MoE-Lightning}: High-Throughput {MoE} Inference on Memory-constrained {GPUs}},56 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},57 booktitle={Proceedings of the 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS)},58 year={2025},59 note={arXiv:2411.11217; ACM DOI not retrieved}60}61@inproceedings{du2024sida,62 title={{SiDA-MoE}: Sparsity-Inspired Data-Aware Serving for Efficient and Scalable Large Mixture-of-Experts Models},63 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},64 booktitle={Proceedings of Machine Learning and Systems (MLSys)},65 year={2024},66 note={arXiv:2310.18859}67}68@article{song2024promoe,69 title={{ProMoE}: Fast {MoE}-based {LLM} Serving using Proactive Caching},70 author={Song, Xiaoniu and Zhong, Zihang and Chen, Rong and Chen, Haibo},71 journal={arXiv preprint arXiv:2410.22134},72 year={2024}73}74@inproceedings{he2026expertflow,75 title={{ExpertFlow}: Efficient Mixture-of-Experts Inference via Predictive Expert Caching and Token Scheduling},76 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},77 booktitle={Proceedings of the Design Automation Conference (DAC)},78 year={2026},79 note={arXiv:2410.17954}80}81@article{yu2025finemoe,82 title={Taming Latency-Memory Trade-Off in {MoE}-Based {LLM} Serving via Fine-Grained Expert Offloading},83 author={Yu, Hanfei and Cui, Xingqi and Zhang, Hong and Wang, Hao and Wang, Hao},84 journal={arXiv preprint arXiv:2502.05370},85 year={2025}86}87@inproceedings{zhang2025daop,88 title={{DAOP}: Data-Aware Offloading and Predictive Pre-Calculation for Efficient {MoE} Inference},89 author={Zhang, Yujie and Aggarwal, Shivam and Mitra, Tulika},90 booktitle={Design, Automation \& Test in Europe Conference (DATE)},91 year={2025},92 note={arXiv:2501.10375}93}94@article{xu2025moegen,95 title={{MoE-Gen}: High-Throughput {MoE} Inference on a Single {GPU} with Module-Based Batching},96 author={Xu, Tairan and Xue, Leyang and Lu, Zhan and Jackson, Adrian and Mai, Luo},97 journal={arXiv preprint arXiv:2503.09716},98 year={2025}99}100@article{fang2025klotski,101 title={Klotski: Efficient Mixture-of-Expert Inference via Expert-Aware Multi-Batch Pipeline},102 author={Fang, Zhiyuan and Huang, Yuegui and Hong, Zicong and Lyu, Yufeng and Chen, Wuhui and Yu, Yue and Yu, Fan and Zheng, Zibin},103 journal={arXiv preprint arXiv:2502.06888},104 year={2025}105}106@article{tairin2025emoe,107 title={{eMoE}: Task-aware Memory Efficient Mixture-of-Experts-Based ({MoE}) Model Inference},108 author={Tairin, Suraiya and Mahmud, Shohaib and Shen, Haiying and Iyer, Anand},109 journal={arXiv preprint arXiv:2503.06823},110 year={2025}111}112@inproceedings{suo2025coserve,113 title={{CoServe}: Efficient Collaboration-of-Experts ({CoE}) Model Inference with Limited Memory},114 author={Suo, Jiashun and Liao, Xiaojian and Xiao, Limin and Ruan, Li and Wang, Jinquan and Su, Xiao and Huo, Zhisheng},115 booktitle={Proceedings of the 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS)},116 year={2025},117 note={arXiv:2503.02354}118}119@article{skliar2025cacheaware,120 title={Mixture of Cache-Conditional Experts for Efficient Mobile Device Inference},121 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},122 journal={Transactions on Machine Learning Research},123 year={2025},124 note={arXiv:2412.00099}125}126@inproceedings{alizadeh2024flash,127 title={{LLM} in a flash: Efficient Large Language Model Inference with Limited Memory},128 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},129 booktitle={Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (ACL)},130 year={2024},131 note={arXiv:2312.11514}132}133@inproceedings{song2024powerinfer,134 title={{PowerInfer}: Fast Large Language Model Serving with a Consumer-grade {GPU}},135 author={Song, Yixin and Mi, Zeyu and Xie, Haotong and Chen, Haibo},136 booktitle={Proceedings of the ACM SIGOPS 30th Symposium on Operating Systems Principles (SOSP)},137 year={2024},138 note={arXiv:2312.12456}139}140@article{huang2023towards,141 title={Towards {MoE} Deployment: Mitigating Inefficiencies in Mixture-of-Expert ({MoE}) Inference},142 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},143 journal={arXiv preprint arXiv:2303.06182},144 year={2023}145}146@inproceedings{cai2024readme,147 title={{Read-ME}: Refactorizing {LLMs} as Router-Decoupled Mixture of Experts with System Co-Design},148 author={Cai, Ruisi and Ro, Yeonju and Kim, Geon-Woo and Wang, Peihao and Ehteshami Bejnordi, Babak and Akella, Aditya and Wang, Zhangyang},149 booktitle={Advances in Neural Information Processing Systems (NeurIPS)},150 year={2024},151 note={arXiv:2410.19123}152}153@article{yao2024exflow,154 title={Exploiting Inter-Layer Expert Affinity for Accelerating Mixture-of-Experts Model Inference},155 author={Yao, Jinghan and Anthony, Quentin and Shafi, Aamir and Subramoni, Hari and Panda, Dhabaleswar K.},156 journal={arXiv preprint arXiv:2401.08383},157 year={2024}158}159@article{fang2025fate,160 title={Fate: Fast Edge Inference of Mixture-of-Experts Models via Cross-Layer Gate},161 author={Fang, Zhiyuan and Hong, Zicong and Huang, Yuegui and Lyu, Yufeng and Chen, Wuhui and Yu, Yue and Yu, Fan and Zheng, Zibin},162 journal={arXiv preprint arXiv:2502.12224},163 year={2025}164}165@inproceedings{liang2026notall,166 title={Not All Models Suit Expert Offloading: On Local Routing Consistency of Mixture-of-Expert Models},167 author={Liang, Jingcong and Wang, Siyuan and Tian, Miren and Li, Yitong and Tang, Duyu and Wei, Zhongyu},168 booktitle={International Conference on Learning Representations (ICLR)},169 year={2026},170 note={arXiv:2505.16056}171}172@inproceedings{zhong2025hybrimoe,173 title={{HybriMoE}: Hybrid {CPU-GPU} Scheduling and Cache Management for Efficient {MoE} Inference},174 author={Zhong, Shuzhang and Sun, Yanfan and Liang, Ling and Wang, Runsheng and Huang, Ru and Li, Meng},175 booktitle={Proceedings of the Design Automation Conference (DAC)},176 year={2025},177 note={arXiv:2504.05897}178}179@inproceedings{huang2026cpugpu,180 title={Efficient {CPU-GPU} Collaborative Inference for {MoE}-based {LLMs} on Memory-Limited Systems},181 author={Huang, En-Ming and Lin, Li-Shang and Lee, Chun-Yi},182 booktitle={Asia and South Pacific Design Automation Conference (ASP-DAC)},183 year={2026},184 note={arXiv:2512.16473}185}186@inproceedings{zhao2026mobile,187 title={{MoBiLE}: Efficient Mixture-of-Experts Inference on Consumer {GPU} with Mixture of Big Little Experts},188 author={Zhao, Yushu and Qin, Yubin and Wang, Yang and Yang, Xiaolong and Han, Huiming and Wei, Shaojun and Hu, Yang and Yin, Shouyi},189 booktitle={Asia and South Pacific Design Automation Conference (ASP-DAC)},190 year={2026},191 note={arXiv:2510.12357}192}193@inproceedings{yu2026layerscope,194 title={{LayerScope}: Predictive Cross-Layer Scheduling for Efficient Multi-Batch {MoE} Inference on Legacy Servers},195 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},196 booktitle={Proceedings of the International Conference on Supercomputing (ICS)},197 year={2026},198 note={arXiv:2509.23638}199}200@article{shen2025expertflow,201 title={{ExpertFlow}: Adaptive Expert Scheduling and Memory Coordination for Efficient {MoE} Inference},202 author={Shen, Zixu and Chu, Kexin and Zhang, Yifan and Xiang, Dawei and Wu, Runxin and Zhang, Wei},203 journal={arXiv preprint arXiv:2510.26730},204 year={2025}205}206@article{zhang2025duoserve,207 title={{DuoServe-MoE}: Dual-Phase Expert Prefetch and Caching for {LLM} Inference {QoS} Assurance},208 author={Zhang, Yuning and Pinkert, Grant and Yang, Nan and Li, Yanli and Yuan, Dong},209 journal={arXiv preprint arXiv:2509.07379},210 year={2025}211}212@article{kim2026flashmoe,213 title={{FlashMoE}: Reducing {SSD} {I/O} Bottlenecks via {ML}-Based Cache Replacement for Mixture-of-Experts Inference on Edge Devices},214 author={Kim, Byeongju and Lee, Jungwan and Han, Donghyeon and Yoo, Hoi-Jun and Kim, Sangyeob},215 journal={arXiv preprint arXiv:2601.17063},216 year={2026}217}218@inproceedings{pan2026trimoe,219 title={{TriMoE}: Augmenting {GPU} with {AMX}-Enabled {CPU} and {DIMM-NDP} for High-Throughput {MoE} Inference via Offloading},220 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},221 booktitle={Proceedings of the Design Automation Conference (DAC)},222 year={2026},223 note={arXiv:2603.01058}224}225@article{kong2026specprefetch,226 title={{SpecPrefetch}: Parameter-Efficient Expert Prefetching for Sparse {MoE} Foundation Models},227 author={Kong, Jinwei and Meng, Runqi and Wang, Fanyi and Qiu, Wentao and Hu, Haotian and Zhou, Yongjian and Ge, Zhenhua},228 journal={arXiv preprint arXiv:2607.24787},229 year={2026}230}231@article{wang2026seqmoe,232 title={{SeqMoE}: Toward Full-Load Performance via Predictive and Graph-Compatible {MoE} Offloading},233 author={Wang, Zihan and Wang, Yuqi and Gong, Lei and Tang, Cheng and Lou, Wenqi and Wang, Teng and Wang, Chao and Zhou, Xuehai},234 journal={arXiv preprint arXiv:2609.12978},235 year={2026}236}237@article{liang2026ssdllama,238 title={{SSD-LLaMA}: {SSD}-Native Inference for Trillion-Parameter {MoE} at 1+ Token/s on a Consumer {PC}},239 author={Liang, Fangzhou and Shen, Yibin and Hu, Jianmin and Xu, Jiayang and Gao, Hanchi and Xu, Minxian and Meng, Zili},240 journal={arXiv preprint arXiv:2609.18110},241 year={2026}242}243@article{yang2026moecore,244 title={{MoE-CORE}: Coordinated Expert Offloading and Residency for Memory-Constrained {MoE} Inference},245 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},246 journal={arXiv preprint arXiv:2610.01950},247 year={2026}248}249@article{yuan2026ordermoe,250 title={{OrderMoE}: An expert similarity driven distributed edge {MoE} inference},251 author={Yuan, Xin and Li, Ning and Chen, Quan and Xu, Wenchao and Guo, Song},252 journal={arXiv preprint arXiv:2607.17154},253 year={2026}254}255@article{benazir2026npumoe,256 title={Efficient Mixture-of-Experts {LLM} Inference with {Apple Silicon} {NPUs}},257 author={Benazir, Afsara and Lin, Felix Xiaozhu},258 journal={arXiv preprint arXiv:2604.18788},259 year={2026}260}261@article{alfarizy2026doesmoe,262 title={Does Mixture-of-Experts Actually Help Inference on Consumer and Edge Hardware? An Empirical Study},263 author={Alfarizy, Alfarizy and Nguyen, Hung Truong Thanh and Richard, Ren{\'e} and Razavi-Far, Roozbeh and Cao, Hung},264 journal={arXiv preprint arXiv:2606.21428},265 year={2026}266}267@inproceedings{kannan2026greenbench,268 title={{GreenBench}: Benchmarking Energy Efficiency and Carbon Footprint of Open-Source {LLM} Inference on {Apple Silicon}},269 author={Kannan, Rajeswari and Firke, Raj and Bengle, Shreya and Deshmukh, Srushti},270 booktitle={IEEE International Conference on Computing, Communication, Control and Automation (ICCUBEA)},271 year={2026},272 note={arXiv:2608.28667}273}274@article{javat2026siliconshowdown,275 title={Silicon Showdown: Performance, Efficiency, and Ecosystem Barriers in Consumer-Grade {LLM} Inference},276 author={Javat, Abdurrahman and Kazakov, Allan},277 journal={arXiv preprint arXiv:2605.00519},278 year={2026}279}280@article{rajesh2025productiongrade,281 title={Production-Grade Local {LLM} Inference on {Apple Silicon}: A Comparative Study of {MLX}, {MLC-LLM}, {Ollama}, {llama.cpp}, and {PyTorch MPS}},282 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},283 journal={arXiv preprint arXiv:2511.05502},284 year={2025}285}286@article{rathnayaka2026basert,287 title={{BaseRT}: Best-in-Class {LLM} Inference on {Apple Silicon} via Native {Metal}},288 author={Rathnayaka, Prabod and Waschkowski, Fabian and Wesemann, Lukas},289 journal={arXiv preprint arXiv:2607.00501},290 year={2026}291}292@article{wilkins2024hybrid,293 title={Hybrid Heterogeneous Clusters Can Lower the Energy Consumption of {LLM} Inference Workloads},294 author={Wilkins, Grant and Keshav, Srinivasan and Mortier, Richard},295 journal={arXiv preprint arXiv:2407.00010},296 year={2024}297}298@inproceedings{borzunov2023petals,299 title={Petals: Collaborative Inference and Fine-tuning of Large Models},300 author={Borzunov, Alexander and Baranchuk, Dmitry and Dettmers, Tim and Riabinin, Maksim and Belkada, Younes and Chumachenko, Artem and Samygin, Pavel and Raffel, Colin},301 booktitle={Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)},302 pages={558--568},303 year={2023},304 doi={10.18653/v1/2023.acl-demo.54}305}306@article{li2025primacpp,307 title={{Prima.cpp}: Fast 30-70B {LLM} Inference on Heterogeneous and Low-Resource Home Clusters},308 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},309 journal={arXiv preprint arXiv:2504.08791},310 year={2025}311}312@misc{exo2025,313 title={exo: Run frontier {AI} locally},314 author={{exo labs}},315 howpublished={\url{https://github.com/exo-explore/exo}},316 year={2025},317 note={Accessed 2026-11-01}318}319@misc{llamacpp2026,320 title={llama.cpp: {LLM} inference in {C/C++}},321 author={Gerganov, Georgi and {ggml-org contributors}},322 howpublished={\url{https://github.com/ggml-org/llama.cpp}},323 year={2026},324 note={Accessed 2026-11-01; RPC backend documented at tools/rpc/README.md}325}326@misc{hannun2023mlx,327 title={{MLX}: Efficient and flexible machine learning on {Apple silicon}},328 author={Hannun, Awni and Digani, Jagrit and Katharopoulos, Angelos and Collobert, Ronan},329 howpublished={\url{https://github.com/ml-explore/mlx}},330 year={2023},331 note={Accessed 2026-11-01; distributed docs: \url{https://ml-explore.github.io/mlx/build/html/usage/distributed.html}}332}333@misc{apple2026mlxdistributed,334 title={Local and Distributed Large {LLM} Inference with {MLX} and {RDMA} on {Mac Studio}},335 author={{Apple Machine Learning Research}},336 howpublished={\url{https://machinelearning.apple.com/research/mlx-distributed-inference}},337 year={2026},338 note={Published 2026-10-15. Accessed 2026-11-01}339}340@misc{apple2026wwdc233,341 title={Explore distributed inference and training with {MLX} ({WWDC26} session 233)},342 author={{Apple Inc.}},343 howpublished={\url{https://developer.apple.com/videos/play/wwdc2026/233/}},344 year={2026},345 note={Accessed 2026-11-01}346}347@misc{geerling2025rdma,348 title={1.5 {TB} of {VRAM} on {Mac Studio} -- {RDMA} over {Thunderbolt 5}},349 author={Geerling, Jeff},350 howpublished={\url{https://jeffgeerling.com/blog/2025/15-tb-vram-on-mac-studio-rdma-over-thunderbolt-5}},351 year={2025},352 note={Blog post, 2025-12-18. Accessed 2026-11-01}353}354@inproceedings{rajbhandari2022deepspeedmoe,355 title={{DeepSpeed-MoE}: Advancing Mixture-of-Experts Inference and Training to Power Next-Generation {AI} Scale},356 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},357 booktitle={Proceedings of the 39th International Conference on Machine Learning (ICML)},358 year={2022},359 note={arXiv:2201.05596}360}361@misc{deepep2025,362 title={{DeepEP}: an efficient expert-parallel communication library},363 author={Zhao, Chenggang and others},364 howpublished={\url{https://github.com/deepseek-ai/DeepEP}},365 year={2025},366 note={Accessed 2026-11-01; author list abbreviated from the repository's own BibTeX}367}368@inproceedings{li2023lina,369 title={Accelerating Distributed {MoE} Training and Inference with {Lina}},370 author={Li, Jiamin and Jiang, Yimin and Zhu, Yibo and Wang, Cong and Xu, Hong},371 booktitle={Proceedings of the USENIX Annual Technical Conference (USENIX ATC)},372 pages={945--959},373 year={2023},374 note={arXiv:2210.17223}375}376@article{hwang2023tutel,377 title={Tutel: Adaptive Mixture-of-Experts at Scale},378 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},379 journal={arXiv preprint arXiv:2206.03382},380 year={2023},381 note={Venue (MLSys 2023) not shown on arXiv page; unverified}382}383@article{gale2023megablocks,384 title={{MegaBlocks}: Efficient Sparse Training with Mixture-of-Experts},385 author={Gale, Trevor and Narayanan, Deepak and Young, Cliff and Zaharia, Matei},386 journal={arXiv preprint arXiv:2211.15841},387 year={2023},388 note={Venue (MLSys 2023) not shown on arXiv page; unverified}389}390@misc{colibri2026,391 title={colibri: Tiny engine, immense model},392 author={Fornaro, Vincenzo},393 howpublished={\url{https://github.com/JustVugg/colibri}},394 year={2026},395 note={Version 2.1.0, Apache-2.0. Accessed 2026-11-01. No paper or citation provided by the project}396}397398% --- added 2026-11-01, verified on arxiv.org/abs pages (title, first authors, date) ---399@article{muennighoff2024olmoe,400 title = {{OLMoE}: Open Mixture-of-Experts Language Models},401 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},402 journal = {arXiv preprint arXiv:2409.02060},403 year = {2024}404}405@article{yang2025qwen3,406 title = {Qwen3 Technical Report},407 author = {Yang, An and Li, Anfeng and Yang, Baosong and others},408 journal = {arXiv preprint arXiv:2505.09388},409 year = {2025}410}411