arXiv subjects

Xuezhu Wang

Publications and source records attributed to Xuezhu Wang.

3 recordsLinked to original sources

arXiv2026

xLLM Technical Report

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.

cs.DC↗

arXiv2025

RLHFSpec: Breaking the Efficiency Bottleneck in RLHF Training via Adaptive Drafting

Reinforcement Learning from Human Feedback (RLHF) is an important fine-tuning technique for large language models (LLMs) and comprises three stages: generation, inference, and training. The generation stage generates samples that are then used to infer learnable experiences for training. We observe that the generation stage is the bottleneck of the entire execution process and consider it a key point for optimization. Specifically, we realize the first attempt to integrate speculative decoding into the RLHF generation stage and propose RLHFSpec, an RLHF system that accelerates generation execution with efficient speculative decoding and sample reallocation. To fully exploit the performance potential provided by speculative decoding, especially dealing with the dynamic workload of the generation stage, RLHFSpec proposes a workload-aware drafting strategy selection mechanism, which selects the near-optimal strategy by jointly considering the verification cost and the number of accepted tokens. Moreover, RLHFSpec also proposes sample reallocation to fully utilize the GPU resources, and optimizes it with an efficient sample migration mechanism. The experimental results show that the RLHFSpec can achieve higher throughput in the generation stage compared to state-of-the-art works. Moreover, due to the effective alleviation of the generation bottleneck, RLHFSpec also shows significant performance speedup in the entire RLHF execution.

cs.LG↗

arXiv2024

Minions: Accelerating Large Language Model Inference with Aggregated Speculative Execution

Large language models (LLM) have recently attracted surging interest due to their outstanding capabilities across various domains. However, enabling efficient LLM inference is challenging due to its autoregressive decoding that generates tokens only one at a time. Although research works apply pruning or quantization to speed up LLM inference, they typically require fine-tuning the LLM, incurring significant time and economic costs. Meanwhile, speculative decoding has been proposed to use small speculative models (SSMs) to accelerate the inference of LLM. However, the low acceptance rate of SSM and the high verification cost of LLM prohibit further performance improvement of inference. In this paper, we propose Minions, an LLM inference system that accelerates LLM inference with a collective and adaptive speculative generation. Specifically, Minions proposes a majority-voted mechanism to leverage multiple SSMs to jointly speculate the outputs of LLM, which improves the inference performance without introducing prohibitive computation costs for LLM. To better trade off the number of tokens speculated from SSM and the verification cost of LLM, Minions proposes an adaptive mechanism to dynamically determine the optimal speculation length of SSM, which can achieve better inference performance across different models, datasets, and hyper-parameters. In addition, Minions decouples the SSM decoding and LLM verification efficiently and adopts a pipelined execution mechanism to further improve the inference performance of LLM. By comparing with the state-of-the-art LLM inference systems, we demonstrate that Minions can achieve higher inference throughput and lower inference time.

cs.DC↗