# Stratos: An End-to-End Distillation Pipeline for Customized LLMs under Distributed Cloud Environments

arXiv: https://arxiv.org/abs/2510.15992 · HTML: https://mlsanity.com/paper/2510.15992/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge distillation for LLMs, one of 12 directions in Knowledge distillation.
- Builds on 8 of its 16 references that are in the map.
- First posted on arXiv 14 Oct 2025.

## Placed in

- Knowledge distillation / [Knowledge distillation for LLMs](https://mlsanity.com/distill/knowledge-distillation-for-llms/)

## Builds on (most cited first, 8 of 8)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://mlsanity.com/paper/2403.13372/) (2024)
- [AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration](https://mlsanity.com/paper/2306.00978/) (2023)
- [Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes](https://mlsanity.com/paper/2305.02301/) (2023)
- [Impossible Distillation: from Low-Quality Model to High-Quality Dataset & Model for Summarization and Paraphrasing](https://mlsanity.com/paper/2305.16635/) (2023)
- [GPT-FL: Generative Pre-trained Model-Assisted Federated Learning](https://mlsanity.com/paper/2306.02210/) (2023)
- [Tailoring Self-Rationalizers with Multi-Reward Distillation](https://mlsanity.com/paper/2311.02805/) (2023)
- [ACME: Adaptive Customization of Large Models via Distributed Systems](https://mlsanity.com/paper/2507.14802/) (2025)

## Built on by (most cited first, 1 of 1)

- [TS-PEFT: Unveiling Token-Level Redundancy in Parameter-Efficient Fine-Tuning](https://mlsanity.com/paper/2511.16147/) (2025)

## Abstract (arXiv)

The growing industrial demand for customized and cost-efficient large language models (LLMs) is fueled by the rise of vertical, domain-specific tasks and the need to optimize performance under constraints such as latency and budget. Knowledge distillation, as an efficient model compression and transfer technique, offers a feasible solution. However, existing distillation frameworks often require manual intervention and struggle to meet such complex user-defined distillation requirements. To bridge this gap, we propose Stratos, an end-to-end LLM distillation pipeline that automates server and model selection, knowledge distillation, and deployment in distributed cloud environments. Given user-defined constraints on model performance and system budget, Stratos automatically selects Pareto-optimal servers, dynamically matches teacher-student pairs, and adapts distillation strategies based on task complexity to optimize cloud hosting. Experiments show that Stratos produces a student model that achieves four times the accuracy of its GPT-4o teacher baseline on a rare, domain-specific Mahjong reasoning task with reverse synthetic data and knowledge injection. Moreover, it achieves reduced latency and cost without compromising accuracy. These results highlight its promise for vertical-domain LLM deployment.