arXiv subjects

Minyi Guo

Publications and source records attributed to Minyi Guo.

At least 91 records · Page 5Linked to original sources

arXiv2025

Lumina: Real-Time Mobile Neural Rendering by Exploiting Computational Redundancy

3D Gaussian Splatting (3DGS) has vastly advanced the pace of neural rendering, but it remains computationally demanding on today's mobile SoCs. To address this challenge, we propose Lumina, a hardware-algorithm co-designed system, which integrates two principal optimizations: a novel algorithm, S^2, and a radiance caching mechanism, RC, to improve the efficiency of neural rendering. S2 algorithm exploits temporal coherence in rendering to reduce the computational overhead, while RC leverages the color integration process of 3DGS to decrease the frequency of intensive rasterization computations. Coupled with these techniques, we propose an accelerator architecture, LuminCore, to further accelerate cache lookup and address the fundamental inefficiencies in Rasterization. We show that Lumina achieves 4.5x speedup and 5.3x energy reduction against a mobile Volta GPU, with a marginal quality loss (< 0.2 dB peak signal-to-noise ratio reduction) across synthetic and real-world datasets.

cs.AR↗

arXiv2025

An Efficient Private GPT Never Autoregressively Decodes

The wide deployment of the generative pre-trained transformer (GPT) has raised privacy concerns for both clients and servers. While cryptographic primitives can be employed for secure GPT inference to protect the privacy of both parties, they introduce considerable performance overhead.To accelerate secure inference, this study proposes a public decoding and secure verification approach that utilizes public GPT models, motivated by the observation that securely decoding one and multiple tokens takes a similar latency. The client uses the public model to generate a set of tokens, which are then securely verified by the private model for acceptance. The efficiency of our approach depends on the acceptance ratio of tokens proposed by the public model, which we improve from two aspects: (1) a private sampling protocol optimized for cryptographic primitives and (2) model alignment using knowledge distillation. Our approach improves the efficiency of secure decoding while maintaining the same level of privacy and generation quality as standard secure decoding. Experiments demonstrate a $2.1\times \sim 6.0\times$ speedup compared to standard decoding across three pairs of public-private models and different network conditions.

cs.CR↗

arXiv2025

Improving the Serving Performance of Multi-LoRA Large Language Models via Efficient LoRA and KV Cache Management

Multiple Low-Rank Adapters (Multi-LoRAs) are gaining popularity for task-specific Large Language Model (LLM) applications. For multi-LoRA serving, caching hot KV caches and LoRA adapters in high bandwidth memory of accelerations can improve inference performance. However, existing Multi-LoRA inference systems fail to optimize serving performance like Time-To-First-Toke (TTFT), neglecting usage dependencies when caching LoRAs and KVs. We therefore propose FASTLIBRA, a Multi-LoRA caching system to optimize the serving performance. FASTLIBRA comprises a dependency-aware cache manager and a performance-driven cache swapper. The cache manager maintains the usage dependencies between LoRAs and KV caches during the inference with a unified caching pool. The cache swapper determines the swap-in or out of LoRAs and KV caches based on a unified cost model, when the HBM is idle or busy, respectively. Experimental results show that ELORA reduces the TTFT by 63.4% on average, compared to state-of-the-art works.

cs.AR↗

arXiv2025

Saga: Capturing Multi-granularity Semantics from Massive Unlabelled IMU Data for User Perception

Inertial measurement units (IMUs), have been prevalently used in a wide range of mobile perception applications such as activity recognition and user authentication, where a large amount of labelled data are normally required to train a satisfactory model. However, it is difficult to label micro-activities in massive IMU data due to the hardness of understanding raw IMU data and the lack of ground truth. In this paper, we propose a novel fine-grained user perception approach, called Saga, which only needs a small amount of labelled IMU data to achieve stunning user perception accuracy. The core idea of Saga is to first pre-train a backbone feature extraction model, utilizing the rich semantic information of different levels embedded in the massive unlabelled IMU data. Meanwhile, for a specific downstream user perception application, Bayesian Optimization is employed to determine the optimal weights for pre-training tasks involving different semantic levels. We implement Saga on five typical mobile phones and evaluate Saga on three typical tasks on three IMU datasets. Results show that when only using about 100 training samples per class, Saga can achieve over 90% accuracy of the full-fledged model trained on over ten thousands training samples with no additional system overhead.

cs.LG↗

arXiv2025

Survey of Disaggregated Memory: Cross-layer Technique Insights for Next-Generation Datacenters

The growing scale of data requires efficient memory subsystems with large memory capacity and high memory performance. Disaggregated architecture has become a promising solution for today's cloud and edge computing for its scalability and elasticity. As a critical part of disaggregation, disaggregated memory faces many design challenges in many dimensions, including hardware scalability, architecture structure, software system design, application programmability, resource allocation, power management, etc. These challenges inspire a number of novel solutions at different system levels to improve system efficiency. In this paper, we provide a comprehensive review of disaggregated memory, including the methodology and technologies of disaggregated memory system foundation, optimization, and management. We study the technical essentials of disaggregated memory systems and analyze them from the hardware, architecture, system, and application levels. Then, we compare the design details of typical cross-layer designs on disaggregated memory. Finally, we discuss the challenges and opportunities of future disaggregated memory works that serve better for next-generation elastic and efficient datacenters.

cs.DC↗

arXiv2025

Efficient Function-as-a-Service for Large Language Models with TIDAL

Large Language Model (LLM) applications have emerged as a prominent use case for Function-as-a-Service (FaaS) due to their high computational demands and sporadic invocation patterns. However, serving LLM functions within FaaS frameworks faces significant GPU-side cold start. A fundamental approach involves leveraging a template with function state saved on GPUs to bypass the cold start for new invocations. Yet, this approach struggles with the high GPU footprint, dynamic initialization behaviors, and lazy GPU kernel loading inherent in LLM functions, primarily due to a lack of insight into the underlying execution details. In this paper, we introduce TIDAL, an optimized FaaS framework for LLM applications that achieves fast startups by tracing fine-grained execution paths. By utilizing the traced execution details, TIDAL generates adaptive function templates, effectively breaking startup barriers for LLM functions. Extensive evaluations demonstrate that TIDAL reduces cold start latency by $1.79\times\text{\textasciitilde}2.11\times$ and improves the $95\%$-ile time-to-first-token by $76.0\%$, surpassing state-of-the-art methods.

cs.OS↗

arXiv2025

Design the Quantum Instruction Set with the Cartan Coordinate Analysis Framework

Most quantum compiling efforts rely on standard two-qubit basis gates, such as CX and iSWAP, to implement general quantum operations. However, with the advancement of quantum architecture design, more nonstandard two-qubit gates can now be implemented and calibrated on devices. Using these nonstandard gates may improve the performance of quantum computation. Despite this potential, it remains unclear how to efficiently incorporate these nonstandard gates into the quantum instruction set to enhance quantum advantage. To address this, we propose an analytical framework that facilitates the design of quantum instruction sets based on nonstandard gates. Our approach is grounded in the KAK decomposition and an analysis of the Cartan coordinate of two-qubit operations, enabling analytical conversion between any two two-qubit operations. This framework also demonstrates the lower and upper bounds of the conversion cost, revealing the relationship between the entangling power of two-qubit instructions and their Cartan coordinates. We further develop a compiler based on the analytical framework, which reduces the unitary decomposition cost with nonstandard two-qubit instructions. Using the proposed compiler, we evaluate various options for designing a quantum instruction set based on nonstandard gates. Our experiments demonstrate the efficiency of the proposed framework in the quantum instruction set design. Compared to the state-of-the-art method that is based on the numerical search, our framework reduces the time/resource overhead of exploring the instruction set design space by thousands of times. Moreover, with the established framework, we propose feasible designs for the quantum instruction set by modeling real-world quantum processors, further promoting the quantum advantage.

quant-ph↗

arXiv2025

M-ANT: Efficient Low-bit Group Quantization for LLMs via Mathematically Adaptive Numerical Type

Large language models (LLMs) are one of the most important killer computer applications. The recent algorithmic advancement proposes a fine-grained group-wise quantization for LLMs, which treats a small set (e.g., 64) of values in a tensor as a compression unit. It effectively preserves the model accuracy without retraining, and has become the standard approach to efficiently deploy LLMs. On the other hand, there are works that propose various adaptive data types to better adapt to different distributions and further reduce the required bit length for LLMs. In this work, our detailed analysis unveils a key finding that while different tensors exhibit similar distributions, small groups can have markedly different distributions. As such, the group-level diversity requires a new level of adaptivity for which existing adaptive data types fail to provide. In this paper, we propose MANT, a mathematically adaptive numeric type, featuring a more flexible encoding paradigm with a wider range of data distribution and more efficient decodingcomputation fusion mechanism to address these challenges. Based on MANT, we develop a supporting framework to assign the appropriate data type for each group adaptively. Meanwhile, the dynamically generated Key-Value (KV) caches in LLMs introduce further complexity for real-time quantization. To tackle this, we propose an efficient real-time quantization mechanism. Besides, we implement a specific processing element (PE) to efficiently support MANT and incorporate a real-time quantization unit. By integrating these components into a systolic array, MANT unifies the group-wise weight and KV cache quantization and addresses the associated challenges. Our evaluation shows achieving, on average, 2.99x (up to 4.46x) speedup and 2.81x (up to 4.10x) energy reduction to the state-of-the-art LLM accelerator.

cs.AR↗

arXiv2025

Revisiting the Design of In-Memory Dynamic Graph Storage

The effectiveness of in-memory dynamic graph storage (DGS) for supporting concurrent graph read and write queries is crucial for real-time graph analytics and updates. Various methods have been proposed, for example, LLAMA, Aspen, LiveGraph, Teseo, and Sortledton. These approaches differ significantly in their support for read and write operations, space overhead, and concurrency control. However, there has been no systematic study to explore the trade-offs among these dimensions. In this paper, we evaluate the effectiveness of individual techniques and identify the performance factors affecting these storage methods by proposing a common abstraction for DGS design and implementing a generic test framework based on this abstraction. Our findings highlight several key insights: 1) Existing DGS methods exhibit substantial space overhead. For example, Aspen consumes 3.3-10.8x more memory than CSR, while the optimal fine-grained methods consume 4.1-8.9x more memory than CSR, indicating a significant memory overhead. 2) Existing methods often overlook memory access impact of modern architectures, leading to performance degradation compared to continuous storage methods. 3) Fine-grained concurrency control methods, in particular, suffer from severe efficiency and space issues due to maintaining versions and performing checks for each neighbor. These methods also experience significant contention on high-degree vertices. Our systematic study reveals these performance bottlenecks and outlines future directions to improve DGS for real-time graph analytics.

cs.DB↗

arXiv2025

A Survey on Inference Optimization Techniques for Mixture of Experts Models

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/.

cs.LG↗

arXiv2025

Prism: Mining Task-aware Domains in Non-i.i.d. IMU Data for Flexible User Perception

A wide range of user perception applications leverage inertial measurement unit (IMU) data for online prediction. However, restricted by the non-i.i.d. nature of IMU data collected from mobile devices, most systems work well only in a controlled setting (e.g., for a specific user in particular postures), limiting application scenarios. To achieve uncontrolled online prediction on mobile devices, referred to as the flexible user perception (FUP) problem, is attractive but hard. In this paper, we propose a novel scheme, called Prism, which can obtain high FUP accuracy on mobile devices. The core of Prism is to discover task-aware domains embedded in IMU dataset, and to train a domain-aware model on each identified domain. To this end, we design an expectation-maximization (EM) algorithm to estimate latent domains with respect to the specific downstream perception task. Finally, the best-fit model can be automatically selected for use by comparing the test sample and all identified domains in the feature space. We implement Prism on various mobile devices and conduct extensive experiments. Results demonstrate that Prism can achieve the best FUP performance with a low latency.

cs.AI↗

arXiv2024

A Microservice Graph Generator with Production Characteristics

A production microservice application may provide multiple services, queries of a service may have different call graphs, and a microservice may be shared across call graphs. It is challenging to improve the resource efficiency of such complex applications without proper benchmarks, while production traces are too large to be used in experiments. To this end, we propose a Service Dependency Graph Generator (DGG) that comprises a Data Handler and a Graph Generator, for generating the service dependency graphs of benchmarks that incorporate production-level characteristics from traces. The data handler first constructs fine-grained call graphs with dynamic interface and repeated calling features from the trace and merges them into dependency graphs, and then clusters them into different categories based on the topological and invocation types. Taking the organized data and the selected category, the graph generator simulates the process of real microservices invoking downstream microservices using a random graph model, generates multiple call graphs, and merges the call graphs to form the small-scale service dependency graph with production-level characteristics. Case studies show that DGG's generated graphs are similar to real traces in terms of topologies. Moreover, the resource scaling based on DGG's fine-grained call graph constructing increases the resource efficiency by up to 44.8% while ensuring the required QoS.

cs.SE↗

arXiv2024

SimGen: Simulator-conditioned Driving Scene Generation

Controllable synthetic data generation can substantially lower the annotation cost of training data. Prior works use diffusion models to generate driving images conditioned on the 3D object layout. However, those models are trained on small-scale datasets like nuScenes, which lack appearance and layout diversity. Moreover, overfitting often happens, where the trained models can only generate images based on the layout data from the validation set of the same dataset. In this work, we introduce a simulator-conditioned scene generation framework called SimGen that can learn to generate diverse driving scenes by mixing data from the simulator and the real world. It uses a novel cascade diffusion pipeline to address challenging sim-to-real gaps and multi-condition conflicts. A driving video dataset DIVA is collected to enhance the generative diversity of SimGen, which contains over 147.5 hours of real-world driving videos from 73 locations worldwide and simulated driving data from the MetaDrive simulator. SimGen achieves superior generation quality and diversity while preserving controllability based on the text prompt and the layout pulled from a simulator. We further demonstrate the improvements brought by SimGen for synthetic data augmentation on the BEV detection and segmentation task and showcase its capability in safety-critical data generation.

cs.CV↗

arXiv2024

Gaze into the Pattern: Characterizing Spatial Patterns with Internal Temporal Correlations for Hardware Prefetching

Hardware prefetching is one of the most widely-used techniques for hiding long data access latency. To address the challenges faced by hardware prefetching, architects have proposed to detect and exploit the spatial locality at the granularity of spatial region. When a new region is activated, they try to find similar previously accessed regions for footprint prediction based on system-level environmental features such as the trigger instruction or data address. However, we find that such context-based prediction cannot capture the essential characteristics of access patterns, leading to limited flexibility, practicality and suboptimal prefetching performance. In this paper, inspired by the temporal property of memory accessing, we note that the temporal correlation exhibited within the spatial footprint is a key feature of spatial patterns. To this end, we propose Gaze, a simple and efficient hardware spatial prefetcher that skillfully utilizes footprint-internal temporal correlations to efficiently characterize spatial patterns. Meanwhile, we observe a unique unresolved challenge in utilizing spatial footprints generated by spatial streaming, which exhibit extremely high access density. Therefore, we further enhance Gaze with a dedicated two-stage approach that mitigates the over-prefetching problem commonly encountered in conventional schemes. Our comprehensive and diverse set of experiments show that Gaze can effectively enhance the performance across a wider range of scenarios. Specifically, Gaze improves performance by 5.7\% and 5.4\% at single-core, 11.4\% and 8.8\% at eight-core, compared to most recent low-cost solutions PMP and vBerti.

cs.AR↗

arXiv2024

Nimbus: Secure and Efficient Two-Party Inference for Transformers

Transformer models have gained significant attention due to their power in machine learning tasks. Their extensive deployment has raised concerns about the potential leakage of sensitive information during inference. However, when being applied to Transformers, existing approaches based on secure two-party computation (2PC) bring about efficiency limitations in two folds: (1) resource-intensive matrix multiplications in linear layers, and (2) complex non-linear activation functions like $\mathsf{GELU}$ and $\mathsf{Softmax}$. This work presents a new two-party inference framework $\mathsf{Nimbus}$ for Transformer models. For the linear layer, we propose a new 2PC paradigm along with an encoding approach to securely compute matrix multiplications based on an outer-product insight, which achieves $2.9\times \sim 12.5\times$ performance improvements compared to the state-of-the-art (SOTA) protocol. For the non-linear layer, through a new observation of utilizing the input distribution, we propose an approach of low-degree polynomial approximation for $\mathsf{GELU}$ and $\mathsf{Softmax}$, which improves the performance of the SOTA polynomial approximation by $2.9\times \sim 4.0\times$, where the average accuracy loss of our approach is 0.08\% compared to the non-2PC inference without privacy. Compared with the SOTA two-party inference, $\mathsf{Nimbus}$ improves the end-to-end performance of \bert{} inference by $2.7\times \sim 4.7\times$ across different network settings.

cs.CR↗

arXiv2024

HOBBIT: A Mixed Precision Expert Offloading System for Fast MoE Inference

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.

cs.LG↗

arXiv2024

Inf-MLLM: Efficient Streaming Inference of Multimodal Large Language Models on a Single GPU

Multimodal Large Language Models (MLLMs) are distinguished by their multimodal comprehensive ability and widely used in many real-world applications including GPT-4o, autonomous driving and robotics. Despite their impressive performance, the multimodal inputs always incur long context. The inference under long context requires caching massive Key and Value states (KV cache) of previous tokens, which introduces high latency and excessive memory consumption. Due to this reason, it is challenging to deploy streaming inference of MLLMs on edge devices, which largely constrains the power and usage of MLLMs in real-world applications. In this paper, we introduce Inf-MLLM, an efficient inference framework for MLLMs, which enable streaming inference of MLLM on a single GPU with infinite context. Inf-MLLM is based on our key observation of the attention pattern in both LLMs and MLLMs called "attention saddles". Thanks to the newly discovered attention pattern, Inf-MLLM maintains a size-constrained KV cache by dynamically caching recent tokens and relevant tokens. Furthermore, Inf-MLLM proposes attention bias, a novel approach to enable MLLMs to capture long-term dependency. We show that Inf-MLLM enables multiple LLMs and MLLMs to achieve stable performance over 4M-token long texts and multi-round conversations with 1-hour-long videos on a single GPU. In addition, Inf-MLLM exhibits superior streaming reasoning quality than existing methods such as StreamingLLM and 2x speedup than H2O.

cs.LG↗

arXiv2024

Potamoi: Accelerating Neural Rendering via a Unified Streaming Architecture

Neural Radiance Field (NeRF) has emerged as a promising alternative for photorealistic rendering. Despite recent algorithmic advancements, achieving real-time performance on today's resource-constrained devices remains challenging. In this paper, we identify the primary bottlenecks in current NeRF algorithms and introduce a unified algorithm-architecture co-design, Potamoi, designed to accommodate various NeRF algorithms. Specifically, we introduce a runtime system featuring a plug-and-play algorithm, SpaRW, which significantly reduces the per-frame computational workload and alleviates compute inefficiencies. Furthermore, our unified streaming pipeline coupled with customized hardware support effectively tames both SRAM and DRAM inefficiencies by minimizing repetitive DRAM access and completely eliminating SRAM bank conflicts. When evaluated against a baseline utilizing a dedicated DNN accelerator, our framework demonstrates a speed-up and energy reduction of 53.1$\times$ and 67.7$\times$, respectively, all while maintaining high visual quality with less than a 1.0 dB reduction in peak signal-to-noise ratio.

cs.AR↗