# BlendServe: Optimizing Offline Inference for Auto-regressive Large Models with Resource-aware Batching

arXiv: https://arxiv.org/abs/2411.16102 · HTML: https://mlsanity.com/paper/2411.16102/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 45 of its 92 references that are in the map.
- First posted on arXiv 25 Nov 2024.

## Builds on (most cited first, 30 of 45)

- [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)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024)
- [Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism](https://mlsanity.com/paper/1909.08053/) (2019)
- [LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding](https://mlsanity.com/paper/2308.14508/) (2023)
- [GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints](https://mlsanity.com/paper/2305.13245/) (2023)
- [SGLang: Efficient Execution of Structured Language Model Programs](https://mlsanity.com/paper/2312.07104/) (2023)
- [DeepSeek LLM: Scaling Open-Source Language Models with Longtermism](https://mlsanity.com/paper/2401.02954/) (2024)
- [WildChat: 1M ChatGPT Interaction Logs in the Wild](https://mlsanity.com/paper/2405.01470/) (2024)
- [DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving](https://mlsanity.com/paper/2401.09670/) (2024)
- [FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU](https://mlsanity.com/paper/2303.06865/) (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)
- [Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference](https://mlsanity.com/paper/2406.10774/) (2024)
- [Ring Attention with Blockwise Transformers for Near-Infinite Context](https://mlsanity.com/paper/2310.01889/) (2023)
- [Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks](https://mlsanity.com/paper/2206.08916/) (2022)
- [OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation](https://mlsanity.com/paper/2407.02371/) (2024)
- [LongVILA: Scaling Long-Context Visual Language Models for Long Videos](https://mlsanity.com/paper/2408.10188/) (2024)
- [Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision, Language, Audio, and Action](https://mlsanity.com/paper/2312.17172/) (2023)
- [VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation](https://mlsanity.com/paper/2409.04429/) (2024)
- [Atom: Low-bit Quantization for Efficient and Accurate LLM Serving](https://mlsanity.com/paper/2310.19102/) (2023)
- [DeepSpeed Ulysses: System Optimizations for Enabling Training of Extreme Long Sequence Transformer Models](https://mlsanity.com/paper/2309.14509/) (2023)
- [PowerInfer: Fast Large Language Model Serving with a Consumer-grade GPU](https://mlsanity.com/paper/2312.12456/) (2023)
- [World Model on Million-Length Video And Language With Blockwise RingAttention](https://mlsanity.com/paper/2402.08268/) (2024)
- [Fast Distributed Inference Serving for Large Language Models](https://mlsanity.com/paper/2305.05920/) (2023)

## Built on by (most cited first, 19 of 19)

- [LMCache: An Efficient KV Cache Layer for Enterprise-Scale LLM Inference](https://mlsanity.com/paper/2510.09665/) (2025)
- [Demystifying Cost-Efficiency in LLM Serving over Heterogeneous GPUs](https://mlsanity.com/paper/2502.00722/) (2025)
- [HyGen: Efficient LLM Serving via Elastic Online-Offline Request Co-location](https://mlsanity.com/paper/2501.14808/) (2025)
- [Accelerating Large-Scale Reasoning Model Inference with Sparse Self-Speculative Decoding](https://mlsanity.com/paper/2512.01278/) (2025)
- [MoE-Gen: High-Throughput MoE Inference on a Single GPU with Module-Based Batching](https://mlsanity.com/paper/2503.09716/) (2025)
- [Optimal Scheduling Algorithms for LLM Inference: Theory and Practice](https://mlsanity.com/paper/2508.01002/) (2025)
- [Cascadia: An Efficient Cascade Serving System for Large Language Models](https://mlsanity.com/paper/2506.04203/) (2025)
- [TokenLake: A Unified Segment-level Prefix Cache Pool for Fine-grained Elastic Long-Context LLM Serving](https://mlsanity.com/paper/2508.17219/) (2025)
- [CoDec: Prefix-Shared Decoding Kernel for LLMs](https://mlsanity.com/paper/2505.17694/) (2025)
- [PROBE: Co-Balancing Computation and Communication in MoE Inference via Real-Time Predictive Prefetching](https://mlsanity.com/paper/2602.00509/) (2026)
- [Echo: Efficient Co-Scheduling of Hybrid Online-Offline Tasks for Large Language Model Serving](https://mlsanity.com/paper/2504.03651/) (2025)
- [ShadowServe: Interference-Free KV Cache Fetching for Distributed Prefix Caching](https://mlsanity.com/paper/2509.16857/) (2025)
- [OServe: Accelerating LLM Serving via Spatial-Temporal Workload Orchestration](https://mlsanity.com/paper/2602.12151/) (2026)
- [Efficient LLM Serving on Hybrid Real-time and Best-effort Requests](https://mlsanity.com/paper/2504.09590/) (2025)
- [MoE-Prefill: Zero Redundancy Overheads in MoE Prefill Serving](https://mlsanity.com/paper/2605.02960/) (2026)
- [PerCache: Predictive Hierarchical Cache for RAG Applications on Mobile Devices](https://mlsanity.com/paper/2601.11553/) (2025)
- [Improving the End-to-End Efficiency of Offline Inference for Multi-LLM Applications Based on Sampling and Simulation](https://mlsanity.com/paper/2503.16893/) (2025)
- [PipeMax: Enhancing Offline LLM Inference on Commodity GPU Servers](https://mlsanity.com/paper/2605.02189/) (2026)
- [HexAGenT: Efficient Agentic LLM Serving via Workflow- and Heterogeneity-Aware Scheduling](https://mlsanity.com/paper/2605.16637/) (2026)

## Abstract (arXiv)

Offline batch inference, which leverages the flexibility of request batching to achieve higher throughput and lower costs, is becoming more popular for latency-insensitive applications. Meanwhile, recent progress in model capability and modality makes requests more diverse in compute and memory demands, creating unique opportunities for throughput improvement by resource overlapping. However, a request schedule that maximizes resource overlapping can conflict with the schedule that maximizes prefix sharing, a widely-used performance optimization, causing sub-optimal inference throughput. We present BlendServe, a system that maximizes resource utilization of offline batch inference by combining the benefits of resource overlapping and prefix sharing using a resource-aware prefix tree. BlendServe exploits the relaxed latency requirements in offline batch inference to reorder and overlap requests with varied resource demands while ensuring high prefix sharing. We evaluate BlendServe on a variety of synthetic multi-modal workloads and show that it provides up to 1.44× throughput boost compared to widely-used industry standards, vLLM and SGLang.