# Cronus: Efficient LLM inference on Heterogeneous GPU Clusters via Partially Disaggregated Prefill

arXiv: https://arxiv.org/abs/2509.17357 · HTML: https://mlsanity.com/paper/2509.17357/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Serving systems and request scheduling, one of 12 directions in Efficient LLM inference and serving.
- Builds on 10 of its 14 references that are in the map.
- First posted on arXiv 22 Sep 2025.

## Placed in

- Efficient LLM inference and serving / [Serving systems and request scheduling](https://mlsanity.com/inference/serving-systems-and-request-scheduling/)

## Builds on (most cited first, 10 of 10)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Splitwise: Efficient generative LLM inference using phase splitting](https://mlsanity.com/paper/2311.18677/) (2023)
- [Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve](https://mlsanity.com/paper/2403.02310/) (2024)
- [SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills](https://mlsanity.com/paper/2308.16369/) (2023)
- [HexGen: Generative Inference of Large Language Model over Heterogeneous Environment](https://mlsanity.com/paper/2311.11514/) (2023)

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

- [Tessera: Unlocking Heterogeneous GPUs through Kernel-Granularity Disaggregation](https://mlsanity.com/paper/2604.10180/) (2026)

## Abstract (arXiv)

Efficient LLM inference is critical for real-world applications, especially within heterogeneous GPU clusters commonly found in organizations and on-premise datacenters as GPU architecture rapidly evolves. Current disaggregated prefill strategies, which separate the prefill and decode stages of LLM inference across different GPUs, often suffer from suboptimal performance due to imbalances between GPU capabilities and workload demands. On the other hand, extending conventional data parallelism and pipeline parallelism to heterogeneous setups incurs high inference latencies. To address these challenges, we introduce Cronus, a novel LLM inference system designed to dynamically balance workloads across heterogeneous GPUs using partially disaggregated prefill. Cronus partitions each prefill stage and executes its initial portion on the low-end GPU, while overlapping the remaining prefill and decode stages of earlier requests on the high-end GPU. Extensive evaluations across various high-end and low-end GPU combinations demonstrate that Cronus significantly improves the throughput over disaggregated prefill. It also reduces TTFT P99 and TBT P99 significantly over DP and PP while maintaining similar or better throughput.