mirror of
https://github.com/hanzoai/papers.git
synced 2026-10-29 07:34:31 +00:00
zeekay
8f118cfc08
9-page paper (mechanism/brain split, memory-aware placement, bilinear utility + LinUCB, SLO objective quality - lambda*cost - mu*latency). Itemized cost model beyond API tokens: honest local-compute electricity figure (~$0.0001/1k tok, not free), cloud-GPU-rental-avoided, run-for-pay fleet angle, seat consolidation, overage avoidance, 1% routing fee, and a 20-person-team TCO table. Builds clean via pdflatex+bibtex.
129 lines
4.7 KiB
BibTeX
129 lines
4.7 KiB
BibTeX
@misc{hanzorouter,
|
|
author = {{Hanzo Industries}},
|
|
title = {{hanzo-router: Memory- and Engine-Aware Model Router}},
|
|
howpublished = {\url{https://github.com/hanzoai/engine}},
|
|
year = {2026}
|
|
}
|
|
|
|
@misc{enso,
|
|
author = {{Hanzo Industries}},
|
|
title = {{enso: Learned SLO-Constrained Routing Policy for hanzo-router}},
|
|
howpublished = {\url{https://github.com/hanzoai/engine}},
|
|
year = {2026}
|
|
}
|
|
|
|
@misc{hanzoengine,
|
|
author = {{Hanzo Industries}},
|
|
title = {{hanzo-engine: An OpenAI-Compatible LLM Inference Engine in Rust}},
|
|
howpublished = {\url{https://github.com/hanzoai/engine}},
|
|
year = {2026}
|
|
}
|
|
|
|
@misc{zenrouter,
|
|
author = {{Zen LM}},
|
|
title = {{zen-router: A 0.6B Trainable Routing Model}},
|
|
howpublished = {\url{https://github.com/zenlm/zen-router}},
|
|
year = {2026}
|
|
}
|
|
|
|
@misc{routellm,
|
|
author = {Isaac Ong and Amjad Almahairi and Vincent Wu and Wei-Lin Chiang and
|
|
Tianhao Wu and Joseph E. Gonzalez and M. Waleed Kadous and Ion Stoica},
|
|
title = {{RouteLLM: Learning to Route LLMs with Preference Data}},
|
|
howpublished = {arXiv preprint arXiv:2406.18665},
|
|
year = {2024}
|
|
}
|
|
|
|
@article{frugalgpt,
|
|
author = {Lingjiao Chen and Matei Zaharia and James Zou},
|
|
title = {{FrugalGPT: How to Use Large Language Models While Reducing Cost
|
|
and Improving Performance}},
|
|
journal = {arXiv preprint arXiv:2305.05176},
|
|
year = {2023}
|
|
}
|
|
|
|
@inproceedings{hybridllm,
|
|
author = {Dujian Ding and Ankur Mallick and Chi Wang and Robert Sim and
|
|
Subhabrata Mukherjee and Victor R{\"u}hle and
|
|
Laks V. S. Lakshmanan and Ahmed Hassan Awadallah},
|
|
title = {{Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing}},
|
|
booktitle = {International Conference on Learning Representations (ICLR)},
|
|
year = {2024}
|
|
}
|
|
|
|
@article{automix,
|
|
author = {Aman Madaan and Pranjal Aggarwal and Ankit Anand and
|
|
Srividya Pranavi Potharaju and Swaroop Mishra and Pei Zhou and
|
|
Aditya Gupta and Dheeraj Rajagopal and Karthik Kappaganthu and
|
|
Yiming Yang and Shyam Upadhyay and Mausam and Manaal Faruqui},
|
|
title = {{AutoMix: Automatically Mixing Language Models}},
|
|
journal = {arXiv preprint arXiv:2310.12963},
|
|
year = {2023}
|
|
}
|
|
|
|
@inproceedings{tabi,
|
|
author = {Yiding Wang and Kai Chen and Haisheng Tan and Kun Guo},
|
|
title = {{Tabi: An Efficient Multi-Level Inference System for Large
|
|
Language Models}},
|
|
booktitle = {Proceedings of the 18th European Conference on Computer Systems
|
|
(EuroSys)},
|
|
year = {2023},
|
|
pages = {233--248},
|
|
publisher = {ACM}
|
|
}
|
|
|
|
@inproceedings{linucb,
|
|
author = {Lihong Li and Wei Chu and John Langford and Robert E. Schapire},
|
|
title = {{A Contextual-Bandit Approach to Personalized News Article
|
|
Recommendation}},
|
|
booktitle = {Proceedings of the 19th International Conference on World Wide Web
|
|
(WWW)},
|
|
year = {2010},
|
|
pages = {661--670},
|
|
publisher = {ACM}
|
|
}
|
|
|
|
@article{ridge,
|
|
author = {Arthur E. Hoerl and Robert W. Kennard},
|
|
title = {{Ridge Regression: Biased Estimation for Nonorthogonal Problems}},
|
|
journal = {Technometrics},
|
|
volume = {12},
|
|
number = {1},
|
|
pages = {55--67},
|
|
year = {1970},
|
|
publisher = {Taylor \& Francis}
|
|
}
|
|
|
|
@article{grpo,
|
|
author = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and
|
|
Junxiao Song and Xiao Bi and Haowei Zhang and Mingchuan Zhang and
|
|
Y. K. Li and Y. Wu and Daya Guo},
|
|
title = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in
|
|
Open Language Models}},
|
|
journal = {arXiv preprint arXiv:2402.03300},
|
|
year = {2024}
|
|
}
|
|
|
|
@misc{runforpay,
|
|
author = {{Hanzo Industries}},
|
|
title = {{Hanzo Cloud Open Edition: Run-for-Pay Pricing and Contributor Revenue}},
|
|
howpublished = {Hanzo architecture note, \url{https://github.com/hanzoai/cloud}},
|
|
year = {2026}
|
|
}
|
|
|
|
@misc{eia,
|
|
author = {{U.S. Energy Information Administration}},
|
|
title = {{Electric Power Monthly: Average Price of Electricity to
|
|
Ultimate Customers by End-Use Sector}},
|
|
howpublished = {\url{https://www.eia.gov/electricity/monthly/}},
|
|
year = {2025}
|
|
}
|
|
|
|
@misc{hickey_simple,
|
|
author = {Rich Hickey},
|
|
title = {{Simple Made Easy}},
|
|
howpublished = {Strange Loop Conference},
|
|
year = {2011},
|
|
note = {\url{https://www.infoq.com/presentations/Simple-Made-Easy/}}
|
|
}
|