# Efficient LLM Serving on Hybrid Real-time and Best-effort Requests

arXiv: https://arxiv.org/abs/2504.09590 · HTML: https://mlsanity.com/paper/2504.09590/

## Key facts

- Cited by 2 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 37 of its 55 references that are in the map.
- First posted on arXiv 13 Apr 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, 30 of 37)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism](https://mlsanity.com/paper/1909.08053/) (2019)
- [Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks](https://mlsanity.com/paper/2204.07705/) (2022)
- [DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving](https://mlsanity.com/paper/2401.09670/) (2024)
- [Recipes for building an open-domain chatbot](https://mlsanity.com/paper/2004.13637/) (2020)
- [FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU](https://mlsanity.com/paper/2303.06865/) (2023)
- [Ray: A Distributed Framework for Emerging AI Applications](https://mlsanity.com/paper/1712.05889/) (2017)
- [Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve](https://mlsanity.com/paper/2403.02310/) (2024)
- [LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset](https://mlsanity.com/paper/2309.11998/) (2023)
- [Ring Attention with Blockwise Transformers for Near-Infinite Context](https://mlsanity.com/paper/2310.01889/) (2023)
- [A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications](https://mlsanity.com/paper/2402.07927/) (2024)
- [FlashInfer: Efficient and Customizable Attention Engine for LLM Inference Serving](https://mlsanity.com/paper/2501.01005/) (2025)
- [DeepSpeed Ulysses: System Optimizations for Enabling Training of Extreme Long Sequence Transformer Models](https://mlsanity.com/paper/2309.14509/) (2023)
- [Can Foundation Models Wrangle Your Data?](https://mlsanity.com/paper/2205.09911/) (2022)
- [Llumnix: Dynamic Scheduling for Large Language Model Serving](https://mlsanity.com/paper/2406.03243/) (2024)
- [Fast Distributed Inference Serving for Large Language Models](https://mlsanity.com/paper/2305.05920/) (2023)
- [DynamoLLM: Designing LLM Inference Clusters for Performance and Energy Efficiency](https://mlsanity.com/paper/2408.00741/) (2024)
- [Language Models Enable Simple Systems for Generating Structured Views of Heterogeneous Data Lakes](https://mlsanity.com/paper/2304.09433/) (2023)

## Built on by (most cited first, 2 of 2)

- [Coordinated Scheduling for MoE LLM Serving](https://mlsanity.com/paper/2606.15177/) (2026)
- [RW-TTT: Batched Serving for Request-Owned Test-Time Training State](https://mlsanity.com/paper/2605.28053/) (2026)

## Abstract (arXiv)

Recent breakthroughs in large Language Models (LLMs) have enabled various generative tasks on a single model. Real-world services (e.g., OpenAI's ChatGPT [27]) powered by an LLM often concurrently support latency-critical requests for interactive applications (e.g., question-answering systems, referred to as real-time or RT requests) and throughput-oriented requests for back-of-house processing (e.g., documents batch processing [28], referred to best-effort or BE requests), with complex hybrid inference workloads to the underlying model. State-of-the-art (SOTA) LLM serving systems dedicate machines to each type of request, towards either low inference latency or high serving throughput, respectively. This practice simplifies request scheduling and management but suffers from poor resource utilization. We propose BROS, a hybrid LLM serving system that aims to collocate RT/BE requests, meeting RT requests' latency requirements while maintaining BE requests' throughput. BROS formulates the problem of hybrid RT/BE request scheduling and solves it with a dynamic priority-based algorithm. BROS designs a bidirectional KV cache management mechanism, allowing RT requests to share KV memory with BE requests to remove the scheduling restrictions caused by insufficient KV memory and improve utilization. Extensive experiments validate that BROS achieves a good trade-off when serving hybrid RT and BE requests. It significantly reduces the latency of RT requests (up to 74.20%), improving their fine-grained service level objectives (SLOs) attainments (up to 36.38x), with negligible throughput reduction for BE requests, showing significant advantages over SOTA systems like vLLM and TGI.