Xiaofeng Hou

Mingzhe Gao, Jieru Zhao, Zhe Lin et al.

Recently, the use of large language models (LLMs) for software code generation, e.g., C/C++ and Python, has proven a great success. However, LLMs still suffer from low syntactic and functional correctness when it comes to the generation of register-transfer level (RTL) code, such as Verilog. To address this issue, in this paper, we develop AutoVCoder, a systematic open-source framework that significantly improves the LLMs' correctness of generating Verilog code and enhances the quality of its output at the same time. Our framework integrates three novel techniques, including a high-quality hardware dataset generation approach, a two-round LLM fine-tuning method and a domain-specific retrieval-augmented generation (RAG) mechanism. Experimental results demonstrate that AutoVCoder outperforms both industrial and academic LLMs in Verilog code generation. Specifically, AutoVCoder shows a 0.5% and 2.2% improvement in functional correctness on the EvalMachine and EvalHuman benchmarks compared with BetterV, and also achieves a 3.4% increase in syntax correctness and a 3.4% increase in functional correctness on the RTLLM benchmark compared with RTLCoder.

Weichuang Zhang, Yiquan Wang, Xinzhou Zhang et al.

FPGAs are well-suited for dataflow architectures that process data in a streaming or pipelined manner, thus satisfying the high computational and communication demands of emerging applications. However, manually implementing an efficient dataflow architecture for large-scale applications is still challenging, even for specialists who use high-level synthesis (HLS) to simplify FPGA programming. To address this, we introduce CODO, an automated compiler that generates feasible and efficient dataflow accelerators on FPGAs. CODO features a systematic method for detecting and eliminating both coarse-grained and fine-grained dataflow violations. Building on this, CODO performs both on- and off-chip data movement optimizations to maximize transfer efficiency. To guarantee a higher design quality, CODO performs automatic scheduling to generate high-performance dataflow accelerators, ensuring a balanced performance-resource trade-off. Synthesis results show that CODO delivers $1.45\times$ to $4.52\times$ latency speedups on typical computation kernels and $3.7\times$ to $33.8\times$ speedups on DNN models compared to SOTA frameworks. In on-board evaluations, CODO achieves $7.3\times$ average speedup on CNN models and $2.07\times$ average speedup on the GPT-2 model over SOTA frameworks. The compiler is open-sourced at https://github.com/sjtu-zhao-lab/codo-artifact.

Jiacheng Liu, Peng Tang, Wenfeng Wang et al.

The emergence of large-scale Mixture of Experts (MoE) models represents a significant advancement in artificial intelligence, offering enhanced model capacity and computational efficiency through conditional computation. However, deploying and running inference on these models presents significant challenges in computational resources, latency, and energy efficiency. This comprehensive survey analyzes optimization techniques for MoE models across the entire system stack. We first establish a taxonomical framework that categorizes optimization approaches into model-level, system-level, and hardware-level optimizations. At the model level, we examine architectural innovations including efficient expert design, attention mechanisms, various compression techniques such as pruning, quantization, and knowledge distillation, as well as algorithm improvement including dynamic routing strategies and expert merging methods. At the system level, we investigate distributed computing approaches, load balancing mechanisms, and efficient scheduling algorithms that enable scalable deployment. Furthermore, we delve into hardware-specific optimizations and co-design strategies that maximize throughput and energy efficiency. This survey provides both a structured overview of existing solutions and identifies key challenges and promising research directions in MoE inference optimization. To facilitate ongoing updates and the sharing of cutting-edge advances in MoE inference optimization research, we have established a repository accessible at https://github.com/MoE-Inf/awesome-moe-inference/.

Wenfeng Wang, Xiaofeng Hou, Peng Tang et al.

Retrieval-Augmented Generation (RAG) systems enhance the performance of large language models (LLMs) by incorporating supplementary retrieved documents, enabling more accurate and context-aware responses. However, integrating these external documents often results in very long input sequences, which significantly increases computation costs during the prefill stage, where key-value (KV) representations for all input tokens are generated. This latency bottleneck becomes especially pronounced under high-throughput serving scenarios. KV-cache reuse offers a promising solution by storing previously computed KV states for shared input prefixes, thereby avoiding redundant computation across requests that contain overlapping context. Yet, the effectiveness of cache reuse is often limited by three practical challenges: low cache hit rates due to naive eviction policies, high CPU-GPU data transfer overhead, and slow SSD I/O when caches spill to storage. To address these issues, we propose PCR, a system designed to maximize KV-cache reuse efficiency through intelligent prefetching and pipelined data movement. Specifically, PCR introduces three key techniques: (1) a prefix-tree caching structure with a look-ahead LRU replacement policy that uses pending requests in the scheduler queue to improve cache hit ratios; (2) layer-wise overlapping that pipelines KV-cache loading and GPU computation across CUDA streams to hide communication latency; and (3) queue-based prefetching that proactively loads relevant KV caches from SSD into DRAM before they are needed. Extensive experiments show that PCR outperforms existing KV-cache reuse methods, achieving up to a 2.47x speedup in terms of average TTFT.

Liang Xu, Jiacheng Liu, Xiang Pan et al.

Data-centric AI has recently proven to be more effective and high-performance, while traditional model-centric AI delivers fewer and fewer benefits. It emphasizes improving the quality of datasets to achieve better model performance. This field has significant potential because of its great practicability and getting more and more attention. However, we have not seen significant research progress in this field, especially in NLP. We propose DataCLUE, which is the first Data-Centric benchmark applied in NLP field. We also provide three simple but effective baselines to foster research in this field (improve Macro-F1 up to 5.7% point). In addition, we conduct comprehensive experiments with human annotators and show the hardness of DataCLUE. We also try an advanced method: the forgetting informed bootstrapping label correction method. All the resources related to DataCLUE, including datasets, toolkit, leaderboard, and baselines, is available online at https://github.com/CLUEbenchmark/DataCLUE

Cheng Xu, Xiaofeng Hou, Jiacheng Liu et al.

Large-scale vision-language mixture-of-experts (VL-MoE) models provide strong multimodal capability, but efficient deployment on memory-constrained platforms remains difficult. Existing MoE offloading systems are largely designed for text-centric workloads and become much less effective for visual-heavy inputs, where large numbers of visual tokens induce broader and less predictable expert accesses. We present VisMMoE, a VL-MoE offloading system built on a single systems insight: pruning redundant visual tokens can improve offloading not only by reducing computation, but also by reshaping expert demand. We refer to this effect as \textit{visual-expert affinity}: token pruning makes expert accesses more concentrated within layers and more stable across layers, producing a smaller and more predictable expert working set. Guided by this insight, VisMMoE combines affinity-aware token compression, lookahead expert prediction, and cache/pipeline orchestration to improve expert locality and prefetch effectiveness under tight memory budgets. We implement VisMMoE on multiple frameworks and evaluate it on representative VL-MoE models and benchmarks. VisMMoE improves end-to-end inference performance by up to 2.68x and 1.61x, respectively, over strong baselines for today's VL-MoE deployments while maintaining competitive accuracy.

Peng Tang, Jiacheng Liu, Xiaofeng Hou et al.

The Mixture-of-Experts (MoE) architecture has demonstrated significant advantages in the era of Large Language Models (LLMs), offering enhanced capabilities with reduced inference costs. However, deploying MoE-based LLMs on memoryconstrained edge devices remains challenging due to their substantial memory requirements. While existing expertoffloading methods alleviate the memory requirements, they often incur significant expert-loading costs or compromise model accuracy. We present HOBBIT, a mixed precision expert offloading system to enable flexible and efficient MoE inference. Our key insight is that dynamically replacing less critical cache-miss experts with low precision versions can substantially reduce expert-loading latency while preserving model accuracy. HOBBIT introduces three innovative techniques that map the natural hierarchy of MoE computation: (1) a token-level dynamic expert loading mechanism, (2) a layer-level adaptive expert prefetching technique, and (3) a sequence-level multidimensional expert caching policy. These innovations fully leverage the benefits of mixedprecision expert inference. By implementing HOBBIT on top of the renowned LLM inference framework Llama.cpp, we evaluate its performance across different edge devices with representative MoE models. The results demonstrate that HOBBIT achieves up to a 9.93x speedup in decoding compared to state-of-the-art MoE offloading systems.

Wenfeng Wang, Jiacheng Liu, Xiaofeng Hou et al.

The immense memory requirements of state-of-the-art Mixture-of-Experts (MoE) models present a significant challenge for inference, often exceeding the capacity of a single accelerator. While offloading experts to host memory is a common solution, it introduces a severe I/O bottleneck over the PCIe bus, as the data-dependent nature of expert selection places these synchronous transfers directly on the critical path of execution, crippling performance. This paper argues that the I/O bottleneck can be overcome by trading a small amount of cheap, on-device computation to hide the immense cost of data movement. We present MoE-SpeQ, a new inference system built on a novel co-design of speculative execution and expert offloading. MoE-SpeQ employs a small, on-device draft model to predict the sequence of required experts for future tokens. This foresight enables a runtime orchestrator to prefetch these experts from host memory, effectively overlapping the expensive I/O with useful computation and hiding the latency from the critical path. To maximize performance, an adaptive governor, guided by an Amortization Roofline Model, dynamically tunes the speculation strategy to the underlying hardware. Our evaluation on memory-constrained devices shows that for the Phi-MoE model, MoE-SpeQ achieves at most 2.34x speedup over the state-of-the-art offloading framework. Our work establishes a new, principled approach for managing data-dependent memory access in resource-limited environments, making MoE inference more accessible on commodity hardware.

Xinfeng Xia, Jiacheng Liu, Xiaofeng Hou et al.

Mixture-of-Experts (MoE) models, the state-of-the-art in large-scale AI, achieve high quality by sparsely activating parameters. However, their reliance on routing between a few monolithic experts via a top-k mechanism creates a "quality cliff", offering only a few coarse-grained operating points. This inflexibility forces a difficult trade-off between cost and quality, preventing adaptation to diverse Service Level Objectives (SLOs) and leading to significant resource over-provisioning. This paper introduces MoE-Prism, a model-system co-design that transforms rigid MoE models into elastic services. Our methodology is divided into two phases. First, an \emph{Offline Refactoring Engine} systematically deconstructs monolithic experts into fine-grained "sub-experts." This engine employs a partitioning optimization solver that uses a metaheuristic-based approach to group neurons, preserving functional locality without requiring retraining. Second, an \emph{Online Scheduling Engine} leverages this new elasticity through QoS-aware scheduling. It implements specialized policies to solve complex system problems, including maximizing throughput in cloud deployments and managing latency-optimized offloading for memory-constrained devices. Our evaluation across three different MoE models shows that MoE-Prismprovides over 4 times more distinct, stable operating points than the baseline. This allows an AI service to dynamically improve throughput by up to 19.9\% under a strict latency budget or reduce latency by up to 10.36\% under limited resources. MoE-Prism provides the critical "control knob" to bridge the model-system gap, enabling the next generation of adaptive, efficient, and QoS-aware AI services.

Zhuo He, Xinwei Zhang, Chen Zhao et al.

Background. Studies have shown that the conventional left ventricular mechanical dyssynchrony (LVMD) parameters have their own statistical limitations. The purpose of this study is to extract new LVMD parameters from the phase analysis of gated SPECT MPI by deep learning to help CRT patient selection. Methods. One hundred and three patients who underwent rest gated SPECT MPI were enrolled in this study. CRT response was defined as a decrease in left ventricular end-systolic volume (LVESV) >= 15% at 6 +- 1 month follow up. Autoencoder (AE), an unsupervised deep learning method, was trained by the raw LV systolic phase polar maps to extract new LVMD parameters, called AE-based LVMD parameters. Correlation analysis was used to explain the relationships between new parameters with conventional LVMD parameters. Univariate and multivariate analyses were used to establish a multivariate model for predicting CRT response. Results. Complete data were obtained in 102 patients, 44.1% of them were classified as CRT responders. AE-based LVMD parameter was significant in the univariate (OR 1.24, 95% CI 1.07 - 1.44, P = 0.006) and multivariate analyses (OR 1.03, 95% CI 1.01 - 1.06, P = 0.006). Moreover, it had incremental value over PSD (AUC 0.72 vs. 0.63, LH 8.06, P = 0.005) and PBW (AUC 0.72 vs. 0.64, LH 7.87, P = 0.005), combined with significant clinic characteristics, including LVEF and gender. Conclusions. The new LVMD parameters extracted by autoencoder from the baseline gated SPECT MPI has the potential to improve the prediction of CRT response.