xLLM Technical Report
By: Tongxuan Liu , Tao Peng , Peijun Yang and more
Potential Business Impact:
Makes smart computer programs run much faster.
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.
Similar Papers
Scalable Engine and the Performance of Different LLM Models in a SLURM based HPC architecture
Distributed, Parallel, and Cluster Computing
Makes smart computer programs run much faster.
An Explorative Study on Distributed Computing Techniques in Training and Inference of Large Language Models
Distributed, Parallel, and Cluster Computing
Lets big AI run on normal computers.
Evaluating Large Language Models for Workload Mapping and Scheduling in Heterogeneous HPC Systems
Distributed, Parallel, and Cluster Computing
Lets computers solve hard scheduling puzzles from words.