# Optimizing Long-context LLM Serving via Fine-grained Sequence Parallelism

arXiv: https://arxiv.org/abs/2511.06247 · HTML: https://mlsanity.com/paper/2511.06247/

## 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 18 of its 35 references that are in the map.
- First posted on arXiv 9 Nov 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, 18 of 18)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis](https://mlsanity.com/paper/2203.13474/) (2022)
- [Splitwise: Efficient generative LLM inference using phase splitting](https://mlsanity.com/paper/2311.18677/) (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)
- [Ring Attention with Blockwise Transformers for Near-Infinite Context](https://mlsanity.com/paper/2310.01889/) (2023)
- [Reducing Activation Recomputation in Large Transformer Models](https://mlsanity.com/paper/2205.05198/) (2022)
- [DeepSpeed Ulysses: System Optimizations for Enabling Training of Extreme Long Sequence Transformer Models](https://mlsanity.com/paper/2309.14509/) (2023)
- [Llumnix: Dynamic Scheduling for Large Language Model Serving](https://mlsanity.com/paper/2406.03243/) (2024)
- [LoongServe: Efficiently Serving Long-Context Large Language Models with Elastic Sequence Parallelism](https://mlsanity.com/paper/2404.09526/) (2024)
- [Striped Attention: Faster Ring Attention for Causal Transformers](https://mlsanity.com/paper/2311.09431/) (2023)
- [Context Parallelism for Scalable Million-Token Inference](https://mlsanity.com/paper/2411.01783/) (2024)
- [Triton-distributed: Programming Overlapping Kernels on Distributed AI Systems with the Triton Compiler](https://mlsanity.com/paper/2504.19442/) (2025)
- [FlexSP: Accelerating Large Language Model Training via Flexible Sequence Parallelism](https://mlsanity.com/paper/2412.01523/) (2024)
- [LoongTrain: Efficient Training of Long-Sequence LLMs with Head-Context Parallelism](https://mlsanity.com/paper/2406.18485/) (2024)

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

- [NanoCP: Request-Level Dynamic Context Parallelism for Data-Expert Parallel Decoding](https://mlsanity.com/paper/2605.21100/) (2026)

## Abstract (arXiv)

With the advancement of large language models (LLMs), their context windows have rapidly expanded. To meet diverse demands from varying-length requests in online services, existing state-of-the-art systems tune the sequence parallelism (SP) allocation. However, current dynamic SP allocation lacks flexibility to (1) support stage-specific parallelism requirements in LLM inference, (2) mitigate the global latency degradation from excessive SP allocation, and (3) exploit resource fragments arising from SP size variation. To tackle this problem, we propose Chunkwise Dynamic Sequence Parallelism (CDSP), a fine-grained parallelism strategy that assigns SP sizes across textitintra-request token segments. Based on CDSP, we build Tetris, an LLM serving system that (1) efficiently integrates CDSP into disaggregated cluster to satisfy parallelism heterogeneity, (2) dynamically regulates SP size expansion based on real-time load conditions, and (3) adaptively explores chunking plans to utilize fragmented resources while meeting per-request demands. Compared with state-of-the-art systems, Tetris achieves up to 4.35× lower time-to-first-token (TTFT) under max sustainable loads, reduces median time-between-tokens (TBT) by up to 40.1%, and increases the max request capacity by up to 45%.