# xLLM Technical Report

arXiv: https://arxiv.org/abs/2510.14686 · HTML: https://mlsanity.com/paper/2510.14686/

## Key facts

- Cited by 3 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 58 of its 90 references that are in the map.
- First posted on arXiv 16 Oct 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 58)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding](https://mlsanity.com/paper/2006.16668/) (2020)
- [Qwen2.5-Coder Technical Report](https://mlsanity.com/paper/2409.12186/) (2024)
- [A Survey on Multimodal Large Language Models](https://mlsanity.com/paper/2306.13549/) (2023)
- [DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models](https://mlsanity.com/paper/2401.06066/) (2024)
- [DeepSeek-VL: Towards Real-World Vision-Language Understanding](https://mlsanity.com/paper/2403.05525/) (2024)
- [MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies](https://mlsanity.com/paper/2404.06395/) (2024)
- [DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving](https://mlsanity.com/paper/2401.09670/) (2024)
- [EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty](https://mlsanity.com/paper/2401.15077/) (2024)
- [Splitwise: Efficient generative LLM inference using phase splitting](https://mlsanity.com/paper/2311.18677/) (2023)
- [EAGLE-2: Faster Inference of Language Models with Dynamic Draft Trees](https://mlsanity.com/paper/2406.16858/) (2024)
- [CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens](https://mlsanity.com/paper/2407.05407/) (2024)
- [TPU v4: An Optically Reconfigurable Supercomputer for Machine Learning with Hardware Support for Embeddings](https://mlsanity.com/paper/2304.01433/) (2023)
- [Recommender Systems with Generative Retrieval](https://mlsanity.com/paper/2305.05065/) (2023)
- [Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations](https://mlsanity.com/paper/2402.17152/) (2024)
- [Inference without Interference: Disaggregate LLM Inference for Mixed Downstream Workloads](https://mlsanity.com/paper/2401.11181/) (2024)
- [LoongServe: Efficiently Serving Long-Context Large Language Models with Elastic Sequence Parallelism](https://mlsanity.com/paper/2404.09526/) (2024)
- [Accelerating Distributed MoE Training and Inference with Lina](https://mlsanity.com/paper/2210.17223/) (2022)
- [vAttention: Dynamic Memory Management for Serving LLMs without PagedAttention](https://mlsanity.com/paper/2405.04437/) (2024)
- [NanoFlow: Towards Optimal Large Language Model Serving Throughput](https://mlsanity.com/paper/2408.12757/) (2024)
- [Generative Recommendation: Towards Next-generation Recommender Paradigm](https://mlsanity.com/paper/2304.03516/) (2023)
- [HLLM: Enhancing Sequential Recommendations via Hierarchical Large Language Models for Item and User Modeling](https://mlsanity.com/paper/2409.12740/) (2024)

## Built on by (most cited first, 3 of 3)

- [RTPrune: Reading-Twice Inspired Token Pruning for Efficient DeepSeek-OCR Inference](https://mlsanity.com/paper/2605.00392/) (2026)
- [xGR: Efficient Generative Recommendation Serving at Scale](https://mlsanity.com/paper/2512.11529/) (2025)
- [ProServe: Unified Multi-Priority Request Scheduling for LLM Serving](https://mlsanity.com/paper/2512.12928/) (2025)

## Abstract (arXiv)

We introduce xLLM, an intelligent and efficient Large Language Model (LLM) inference framework designed for high-performance, large-scale enterprise-grade serving, with deep optimizations for diverse AI accelerators. To address these challenges, xLLM builds a novel decoupled service-engine architecture. At the service layer, xLLM-Service features an intelligent scheduling module that efficiently processes multimodal requests and co-locates online and offline tasks through unified elastic scheduling to maximize cluster utilization. This module also relies on a workload-adaptive dynamic Prefill-Decode (PD) disaggregation policy and a novel Encode-Prefill-Decode (EPD) disaggregation policy designed for multimodal inputs. Furthermore, it incorporates a distributed architecture to provide global KV Cache management and robust fault-tolerant capabilities for high availability. At the engine layer, xLLM-Engine co-optimizes system and algorithm designs to fully saturate computing resources. This is achieved through comprehensive multi-layer execution pipeline optimizations, an adaptive graph mode and an xTensor memory management. xLLM-Engine also further integrates algorithmic enhancements such as optimized speculative decoding and dynamic EPLB, collectively serving to substantially boost throughput and inference efficiency. Extensive evaluations demonstrate that xLLM delivers significantly superior performance and resource efficiency. Under identical TPOT constraints, xLLM achieves throughput up to 1.7x that of MindIE and 2.2x that of vLLM-Ascend with Qwen-series models, while maintaining an average throughput of 1.7x that of MindIE with Deepseek-series models. xLLM framework is publicly available at https://github.com/jd-opensource/xllm and https://github.com/jd-opensource/xllm-service.