中文
相关论文

相关论文: Ascend-RaBitQ: Heterogeneous NPU-CPU Acceleration …

200 篇论文

Billion-scale high-dimensional approximate nearest neighbour (ANN) search has become an important problem for searching similar objects among the vast amount of images and videos available online. The existing ANN methods are usually…

计算机视觉与模式识别 · 计算机科学 2019-07-30 Wei Chen , Jincai Chen , Fuhao Zou , Yuan-Fang Li , Ping Lu , Qiang Wang , Wei Zhao

Approximate nearest neighbor search (ANNS) on GPUs is gaining increasing popularity for modern retrieval and recommendation workloads that operate over massive high-dimensional vectors. Graph-based indexes deliver high recall and throughput…

数据库 · 计算机科学 2026-03-02 Jifan Shi , Jianyang Gao , James Xia , Tamás Béla Fehér , Cheng Long

Nowadays, data is represented by vectors. Retrieving those vectors, among millions and billions, that are similar to a given query is a ubiquitous problem, known as similarity search, of relevance for a wide range of applications.…

机器学习 · 计算机科学 2023-07-26 Cecilia Aguerrebere , Ishwar Bhati , Mark Hildebrand , Mariano Tepper , Ted Willke

Retrieving the most similar vector embeddings to a given query among a massive collection of vectors has long been a key component of countless real-world applications. The recently introduced Retrieval-Augmented Generation is one of the…

机器学习 · 计算机科学 2024-02-06 Cecilia Aguerrebere , Mark Hildebrand , Ishwar Singh Bhati , Theodore Willke , Mariano Tepper

The co-design of neural network architectures, quantization precisions, and hardware accelerators offers a promising approach to achieving an optimal balance between performance and efficiency, particularly for model deployment on…

计算机视觉与模式识别 · 计算机科学 2025-01-10 Mingzi Wang , Yuan Meng , Chen Tang , Weixiang Zhang , Yijian Qin , Yang Yao , Yingxin Li , Tongtong Feng , Xin Wang , Xun Guan , Zhi Wang , Wenwu Zhu

Quantization methods have been introduced to perform large scale approximate nearest search tasks. Residual Vector Quantization (RVQ) is one of the effective quantization methods. RVQ uses a multi-stage codebook learning scheme to lower the…

计算机视觉与模式识别 · 计算机科学 2015-09-18 Shicong Liu , Hongtao Lu , Junru Shao

We design and implement parallel prefix sum (scan) algorithms using Ascend AI accelerators. Ascend accelerators feature specialized computing units: the cube units for efficient matrix multiplication and the vector units for optimized…

分布式、并行与集群计算 · 计算机科学 2026-01-05 Bartłomiej Wróblewski , Gioele Gottardo , Anastasios Zouzias

Approximate Nearest Neighbor Search (ANNS) underpins modern applications such as information retrieval and recommendation. With the rapid growth of vector data, efficient indexing for real-time vector search has become rudimentary. Existing…

数据库 · 计算机科学 2026-01-14 Yuchen Peng , Dingyu Yang , Zhongle Xie , Ji Sun , Lidan Shou , Ke Chen , Gang Chen

We develop methods for accelerating metric similarity search that are effective on modern hardware. Our algorithms factor into easily parallelizable components, making them simple to deploy and efficient on multicore CPUs and GPUs. Despite…

数据库 · 计算机科学 2016-11-15 Lawrence Cayton

Approximate nearest neighbor (ANN) query in high-dimensional Euclidean space is a key operator in database systems. For this query, quantization is a popular family of methods developed for compressing vectors and reducing memory…

数据库 · 计算机科学 2024-09-17 Jianyang Gao , Yutong Gou , Yuexuan Xu , Yongyi Yang , Cheng Long , Raymond Chi-Wing Wong

Post-Training Quantization (PTQ) is crucial for efficient model deployment, yet its effectiveness on Ascend NPU remains under-explored compared to GPU architectures. This paper presents a case study of representative PTQ baselines applied…

机器学习 · 计算机科学 2026-02-23 Yuchen Luo , Fangyue Zhu , Ruining Zhou , Mingzhe Huang , Jian Zhu , Fanyu Fan , Wei Shao

Embedding vectors are widely used for representing unstructured data and searching through it for semantically similar items. However, the large size of these vectors, due to their high-dimensionality, creates problems for modern vector…

机器学习 · 计算机科学 2025-09-24 Mariano Tepper , Ted Willke

Recent one-shot Neural Architecture Search algorithms rely on training a hardware-agnostic super-network tailored to a specific task and then extracting efficient sub-networks for different hardware platforms. Popular approaches separate…

机器学习 · 计算机科学 2023-12-22 Sharath Nittur Sridhar , Maciej Szankin , Fang Chen , Sairam Sundaresan , Anthony Sarah

This paper presents a novel approach for similarity search with complex filtering capabilities on billion-scale datasets, optimized for CPU inference. Our method extends the classical IVF-Flat index structure to integrate multi-dimensional…

信息检索 · 计算机科学 2025-01-24 Simeon Emanuilov , Aleksandar Dimov

The steady progress of quantum hardware is motivating the search for novel quantum algorithm optimization strategies for near-term, real-world applications. In this study, we propose a novel feature map optimization strategy for Quantum…

量子物理 · 物理学 2025-03-31 Roberto Moretti , Andrea Giachero , Voica Radescu , Michele Grossi

Similarity search in high-dimentional spaces is a pivotal operation found a variety of database applications. Recently, there has been an increase interest in similarity search for online content-based multimedia services. Those services,…

多媒体 · 计算机科学 2012-09-04 George Teodoro , Eduardo Valle , Nathan Mariano , Ricardo Torres , Wagner Meira , Joel H. Saltz

Large language models (LLMs) are increasingly deployed on edge devices. To meet strict resource constraints, real-world deployment has pushed LLM quantization from 8-bit to 4-bit, 2-bit, and now 1.58-bit. Combined with lookup table…

分布式、并行与集群计算 · 计算机科学 2026-04-15 Xiangyu Li , Chengyu Yin , Weijun Wang , Jianyu Wei , Ting Cao , Yunxin Liu

We present APQ for efficient deep learning inference on resource-constrained hardware. Unlike previous methods that separately search the neural architecture, pruning policy, and quantization policy, we optimize them in a joint manner. To…

机器学习 · 计算机科学 2020-06-16 Tianzhe Wang , Kuan Wang , Han Cai , Ji Lin , Zhijian Liu , Song Han

Concurrent priority queues are widely used in important workloads, such as graph applications and discrete event simulations. However, designing scalable concurrent priority queues for NUMA architectures is challenging. Even though several…

分布式、并行与集群计算 · 计算机科学 2024-06-12 Christina Giannoula , Foteini Strati , Dimitrios Siakavaras , Georgios Goumas , Nectarios Koziris

Edge computing's growing prominence, due to its ability to reduce communication latency and enable real-time processing, is promoting the rise of high-performance, heterogeneous System-on-Chip solutions. While current approaches often…

人工智能 · 计算机科学 2024-09-24 Rakshith Jayanth , Neelesh Gupta , Viktor Prasanna
‹ 上一页 1 2 3 10 下一页 ›