arXiv subjects

Yongji Wu

Publications and source records attributed to Yongji Wu.

31 records · Page 2Linked to original sources

arXiv2025

Plato: Plan to Efficiently Decode for Large Language Model Inference

Large language models (LLMs) have achieved remarkable success in natural language tasks, but their inference incurs substantial computational and memory overhead. To improve efficiency, parallel decoding methods like Skeleton-of-Thought (SoT) decompose prompts into sub-problems for concurrent processing. However, these methods significantly compromise answer quality by treating semantically linked sub-problems as independent. We propose Plato, a novel approach that co-designs algorithms and systems for semantic-aware parallel decoding. Plato leverages LLMs to organize sub-problems into a dependency graph based on logical and causal relationships, enabling concurrent decoding of non-dependent nodes while preserving answer coherence and quality. To further enhance efficiency, Plato pipelines planning and node decoding stages, implements a global context cache, and carefully structures node inference prompts to maximize key-value cache reuse and minimize overhead. Our evaluations show that Plato improves throughput by 68% over autoregressive decoding while achieving a 40% net win rate in answer quality. Compared to SoT, Plato demonstrates a remarkable 90% quality net-win rate. Ablation studies reveal that our pipeline design improves speedup by 29%, while our KV cache reuse optimization reduces overhead by 75%.

cs.CL↗

arXiv2025

HeterMoE: Efficient Training of Mixture-of-Experts Models on Heterogeneous GPUs

The Mixture-of-Experts (MoE) architecture has become increasingly popular as a method to scale up large language models (LLMs). To save costs, heterogeneity-aware training solutions have been proposed to utilize GPU clusters made up of both newer and older-generation GPUs. However, existing solutions are agnostic to the performance characteristics of different MoE model components (i.e., attention and expert) and do not fully utilize each GPU's compute capability. In this paper, we introduce HeterMoE, a system to efficiently train MoE models on heterogeneous GPUs. Our key insight is that newer GPUs significantly outperform older generations on attention due to architectural advancements, while older GPUs are still relatively efficient for experts. HeterMoE disaggregates attention and expert computation, where older GPUs are only assigned with expert modules. Through the proposed zebra parallelism, HeterMoE overlaps the computation on different GPUs, in addition to employing an asymmetric expert assignment strategy for fine-grained load balancing to minimize GPU idle time. Our evaluation shows that HeterMoE achieves up to 2.3x speed-up compared to existing MoE training systems, and 1.4x compared to an optimally balanced heterogeneity-aware solution. HeterMoE efficiently utilizes older GPUs by maintaining 95% training throughput on average, even with half of the GPUs in a homogeneous A40 cluster replaced with V100.

cs.DC↗

arXiv2024

VcLLM: Video Codecs are Secretly Tensor Codecs

As the parameter size of large language models (LLMs) continues to expand, the need for a large memory footprint and high communication bandwidth have become significant bottlenecks for the training and inference of LLMs. To mitigate these bottlenecks, various tensor compression techniques have been proposed to reduce the data size, thereby alleviating memory requirements and communication pressure. Our research found that video codecs, despite being originally designed for compressing videos, show excellent efficiency when compressing various types of tensors. We demonstrate that video codecs can be versatile and general-purpose tensor codecs while achieving the state-of-the-art compression efficiency in various tasks. We further make use of the hardware video encoding and decoding module available on GPUs to create a framework capable of both inference and training with video codecs repurposed as tensor codecs. This greatly reduces the requirement for memory capacity and communication bandwidth, enabling training and inference of large models on consumer-grade GPUs.

cs.LG↗

arXiv2024

Computing in the Era of Large Generative Models: From Cloud-Native to AI-Native

In this paper, we investigate the intersection of large generative AI models and cloud-native computing architectures. Recent large models such as ChatGPT, while revolutionary in their capabilities, face challenges like escalating costs and demand for high-end GPUs. Drawing analogies between large-model-as-a-service (LMaaS) and cloud database-as-a-service (DBaaS), we describe an AI-native computing paradigm that harnesses the power of both cloud-native technologies (e.g., multi-tenancy and serverless computing) and advanced machine learning runtime (e.g., batched LoRA inference). These joint efforts aim to optimize costs-of-goods-sold (COGS) and improve resource accessibility. The journey of merging these two domains is just at the beginning and we hope to stimulate future research and development in this area.

cs.DC↗

arXiv2024

Curator: Efficient Indexing for Multi-Tenant Vector Databases

Vector databases have emerged as key enablers for bridging intelligent applications with unstructured data, providing generic search and management support for embedding vectors extracted from the raw unstructured data. As multiple data users can share the same database infrastructure, multi-tenancy support for vector databases is increasingly desirable. This hinges on an efficient filtered search operation, i.e., only querying the vectors accessible to a particular tenant. Multi-tenancy in vector databases is currently achieved by building either a single, shared index among all tenants, or a per-tenant index. The former optimizes for memory efficiency at the expense of search performance, while the latter does the opposite. Instead, this paper presents Curator, an in-memory vector index design tailored for multi-tenant queries that simultaneously achieves the two conflicting goals, low memory overhead and high performance for queries, vector insertion, and deletion. Curator indexes each tenant's vectors with a tenant-specific clustering tree and encodes these trees compactly as sub-trees of a shared clustering tree. Each tenant's clustering tree adapts dynamically to its unique vector distribution, while maintaining a low per-tenant memory footprint. Our evaluation, based on two widely used data sets, confirms that Curator delivers search performance on par with per-tenant indexing, while maintaining memory consumption at the same level as metadata filtering on a single, shared index.

cs.DB↗

arXiv2023

AR Visualization System for Ship Detection and Recognition Based on AI

Augmented reality technology has been widely used in industrial design interaction, exhibition guide, information retrieval and other fields. The combination of artificial intelligence and augmented reality technology has also become a future development trend. This project is an AR visualization system for ship detection and recognition based on AI, which mainly includes three parts: artificial intelligence module, Unity development module and Hololens2AR module. This project is based on R3Det algorithm to complete the detection and recognition of ships in remote sensing images. The recognition rate of model detection trained on RTX 2080Ti can reach 96%. Then, the 3D model of the ship is obtained by ship categories and information and generated in the virtual scene. At the same time, voice module and UI interaction module are added. Finally, we completed the deployment of the project on Hololens2 through MRTK. The system realizes the fusion of computer vision and augmented reality technology, which maps the results of object detection to the AR field, and makes a brave step toward the future technological trend and intelligent application.

cs.CV↗

arXiv2023

Punica: Multi-Tenant LoRA Serving

Low-rank adaptation (LoRA) has become an important and popular method to adapt pre-trained models to specific domains. We present Punica, a system to serve multiple LoRA models in a shared GPU cluster. Punica contains a new CUDA kernel design that allows batching of GPU operations for different LoRA models. This allows a GPU to hold only a single copy of the underlying pre-trained model when serving multiple, different LoRA models, significantly enhancing GPU efficiency in terms of both memory and computation. Our scheduler consolidates multi-tenant LoRA serving workloads in a shared GPU cluster. With a fixed-sized GPU cluster, our evaluations show that Punica achieves 12x higher throughput in serving multiple LoRA models compared to state-of-the-art LLM serving systems while only adding 2ms latency per token. Punica is open source at https://github.com/punica-ai/punica .

cs.DC↗

arXiv2023

Remote Procedure Call as a Managed System Service

Remote Procedure Call (RPC) is a widely used abstraction for cloud computing. The programmer specifies type information for each remote procedure, and a compiler generates stub code linked into each application to marshal and unmarshal arguments into message buffers. Increasingly, however, application and service operations teams need a high degree of visibility and control over the flow of RPCs between services, leading many installations to use sidecars or service mesh proxies for manageability and policy flexibility. These sidecars typically involve inspection and modification of RPC data that the stub compiler had just carefully assembled, adding needless overhead. Further, upgrading diverse application RPC stubs to use advanced hardware capabilities such as RDMA or DPDK is a long and involved process, and often incompatible with sidecar policy control. In this paper, we propose, implement, and evaluate a novel approach, where RPC marshalling and policy enforcement are done as a system service rather than as a library linked into each application. Applications specify type information to the RPC system as before, while the RPC service executes policy engines and arbitrates resource use, and then marshals data customized to the underlying network hardware capabilities. Our system, mRPC, also supports live upgrades so that both policy and marshalling code can be updated transparently to application code. Compared with using a sidecar, mRPC speeds up a standard microservice benchmark, DeathStarBench, by up to 2.5$\times$ while having a higher level of policy flexibility and availability.

cs.NI↗

arXiv2022

Serving and Optimizing Machine Learning Workflows on Heterogeneous Infrastructures

With the advent of ubiquitous deployment of smart devices and the Internet of Things, data sources for machine learning inference have increasingly moved to the edge of the network. Existing machine learning inference platforms typically assume a homogeneous infrastructure and do not take into account the more complex and tiered computing infrastructure that includes edge devices, local hubs, edge datacenters, and cloud datacenters. On the other hand, recent AutoML efforts have provided viable solutions for model compression, pruning and quantization for heterogeneous environments; for a machine learning model, now we may easily find or even generate a series of models with different tradeoffs between accuracy and efficiency. We design and implement JellyBean, a system for serving and optimizing machine learning inference workflows on heterogeneous infrastructures. Given service-level objectives (e.g., throughput, accuracy), JellyBean picks the most cost-efficient models that meet the accuracy target and decides how to deploy them across different tiers of infrastructures. Evaluations show that JellyBean reduces the total serving cost of visual question answering by up to 58%, and vehicle tracking from the NVIDIA AI City Challenge by up to 36% compared with state-of-the-art model selection and worker assignment solutions. JellyBean also outperforms prior ML serving systems (e.g., Spark on the cloud) up to 5x in serving costs.

cs.LG↗

arXiv2021

Poisoning Attacks to Local Differential Privacy Protocols for Key-Value Data

Local Differential Privacy (LDP) protocols enable an untrusted server to perform privacy-preserving, federated data analytics. Various LDP protocols have been developed for different types of data such as categorical data, numerical data, and key-value data. Due to their distributed settings, LDP protocols are fundamentally vulnerable to poisoning attacks, in which fake users manipulate the server's analytics results via sending carefully crafted data to the server. However, existing poisoning attacks focused on LDP protocols for simple data types such as categorical and numerical data, leaving the security of LDP protocols for more advanced data types such as key-value data unexplored. In this work, we aim to bridge the gap by introducing novel poisoning attacks to LDP protocols for key-value data. In such a LDP protocol, a server aims to simultaneously estimate the frequency and mean value of each key among some users, each of whom possesses a set of key-value pairs. Our poisoning attacks aim to simultaneously maximize the frequencies and mean values of some attacker-chosen target keys via sending carefully crafted data from some fake users to the sever. Specifically, since our attacks have two objectives, we formulate them as a two-objective optimization problem. Moreover, we propose a method to approximately solve the two-objective optimization problem, from which we obtain the optimal crafted data the fake users should send to the server. We demonstrate the effectiveness of our attacks to three LDP protocols for key-value data both theoretically and empirically. We also explore two defenses against our attacks, which are effective in some scenarios but have limited effectiveness in other scenarios. Our results highlight the needs for new defenses against our poisoning attacks.

cs.CR↗

arXiv2021

How Powerful is Graph Convolution for Recommendation?

Graph convolutional networks (GCNs) have recently enabled a popular class of algorithms for collaborative filtering (CF). Nevertheless, the theoretical underpinnings of their empirical successes remain elusive. In this paper, we endeavor to obtain a better understanding of GCN-based CF methods via the lens of graph signal processing. By identifying the critical role of smoothness, a key concept in graph signal processing, we develop a unified graph convolution-based framework for CF. We prove that many existing CF methods are special cases of this framework, including the neighborhood-based methods, low-rank matrix factorization, linear auto-encoders, and LightGCN, corresponding to different low-pass filters. Based on our framework, we then present a simple and computationally efficient CF baseline, which we shall refer to as Graph Filter based Collaborative Filtering (GF-CF). Given an implicit feedback matrix, GF-CF can be obtained in a closed form instead of expensive training with back-propagation. Experiments will show that GF-CF achieves competitive or better performance against deep learning-based methods on three well-known datasets, notably with a $70\%$ performance gain over LightGCN on the Amazon-book dataset.

cs.IR↗

arXiv2021

Rethinking Lifelong Sequential Recommendation with Incremental Multi-Interest Attention

Sequential recommendation plays an increasingly important role in many e-commerce services such as display advertisement and online shopping. With the rapid development of these services in the last two decades, users have accumulated a massive amount of behavior data. Richer sequential behavior data has been proven to be of great value for sequential recommendation. However, traditional sequential models fail to handle users' lifelong sequences, as their linear computational and storage cost prohibits them from performing online inference. Recently, lifelong sequential modeling methods that borrow the idea of memory networks from NLP are proposed to address this issue. However, the RNN-based memory networks built upon intrinsically suffer from the inability to capture long-term dependencies and may instead be overwhelmed by the noise on extremely long behavior sequences. In addition, as the user's behavior sequence gets longer, more interests would be demonstrated in it. It is therefore crucial to model and capture the diverse interests of users. In order to tackle these issues, we propose a novel lifelong incremental multi-interest self attention based sequential recommendation model, namely LimaRec. Our proposed method benefits from the carefully designed self-attention to identify relevant information from users' behavior sequences with different interests. It is still able to incrementally update users' representations for online inference, similarly to memory network based approaches. We extensively evaluate our method on four real-world datasets and demonstrate its superior performances compared to the state-of-the-art baselines.

cs.IR↗

arXiv2021

Linear-Time Self Attention with Codeword Histogram for Efficient Recommendation

Self-attention has become increasingly popular in a variety of sequence modeling tasks from natural language processing to recommendation, due to its effectiveness. However, self-attention suffers from quadratic computational and memory complexities, prohibiting its applications on long sequences. Existing approaches that address this issue mainly rely on a sparse attention context, either using a local window, or a permuted bucket obtained by locality-sensitive hashing (LSH) or sorting, while crucial information may be lost. Inspired by the idea of vector quantization that uses cluster centroids to approximate items, we propose LISA (LInear-time Self Attention), which enjoys both the effectiveness of vanilla self-attention and the efficiency of sparse attention. LISA scales linearly with the sequence length, while enabling full contextual attention via computing differentiable histograms of codeword distributions. Meanwhile, unlike some efficient attention methods, our method poses no restriction on casual masking or sequence length. We evaluate our method on four real-world datasets for sequential recommendation. The results show that LISA outperforms the state-of-the-art efficient attention methods in both performance and speed; and it is up to 57x faster and 78x more memory efficient than vanilla self-attention.

cs.IR↗