相关论文: GPU-Accelerated Viterbi Exact Lattice Decoder for …

This paper presents a GPU-accelerated computational framework for reconstructing high resolution (HR) LF images under a mixed Gaussian-Impulse noise condition. The main focus is on developing a high-performance approach considering…

The vast majority of inference time for RNN Transducer (RNN-T) models today is spent on decoding. Current state-of-the-art RNN-T decoding implementations leave the GPU idle ~80% of the time. Leveraging a new CUDA 12.4 feature, CUDA graph…

Low-latency decoding for large language models (LLMs) is crucial for applications like chatbots and code assistants, yet generating long outputs remains slow in single-query settings. Prior work on speculative decoding (which combines a…

Recently, the unified streaming and non-streaming two-pass (U2/U2++) end-to-end model for speech recognition has shown great performance in terms of streaming capability, accuracy and latency. In this paper, we present fast-U2++, an…

Computational fluid dynamic simulations often produce large clusters of finite elements with non-trivial, non-convex boundaries and uneven distributions among compute nodes, posing challenges to compositing during interactive volume…

Transformer-based neural models are used in many AI applications. Training these models is expensive, as it takes huge GPU resources and long duration. It is challenging because typical data like sentences have variable lengths, and…

Transformers have become a predominant machine learning workload, they are not only the de-facto standard for natural language processing tasks, but they are also being deployed in other domains such as vision and speech recognition. Many…

Field Programmable Gate Array technology (FPGA) is a highly configurable option for implementing many sophisticated signal processing tasks in Software Defined Radios (SDRs). Those types of radios are realized using highly configurable…

Despite significant progress in Video Large Language Models (Video-LLMs) for offline video understanding, existing online Video-LLMs typically struggle to simultaneously process continuous frame-by-frame inputs and determine optimal…

FFT (fast Fourier transform) plays a very important role in many fields, such as digital signal processing, digital image processing and so on. However, in application, FFT becomes a factor of affecting the processing efficiency, especially…

We present SURGE, a streaming GPU encoding system deployed in production to generate embeddings for over 800 million texts across 40,000 logical partitions. Production embedding pipelines face a tension between logical data partitioning and…

Adaptive finite elements combined with geometric multigrid solvers are one of the most efficient numerical methods for problems such as the instationary Navier-Stokes equations. Yet despite their efficiency, computations remain expensive…

GPU-accelerated computing is a key technology to realize high-speed inference servers using deep neural networks (DNNs). An important characteristic of GPU-based inference is that the computational efficiency, in terms of the processing…

Attention encoder-decoder model architecture is the backbone of several recent top performing foundation speech models: Whisper, Seamless, OWSM, and Canary-1B. However, the reported data and compute requirements for their training are…

With increasingly more powerful compute capabilities and resources in today's devices, traditionally compute-intensive automatic speech recognition (ASR) has been moving from the cloud to devices to better protect user privacy. However, it…

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…

Fisher vector has been widely used in many multimedia retrieval and visual recognition applications with good performance. However, the computation complexity prevents its usage in real-time video monitoring. In this work, we proposed and…

With the growing demand for deploying deep learning models to the "edge", it is paramount to develop techniques that allow to execute state-of-the-art models within very tight and limited resource constraints. In this work we propose a…

Two widely adopted techniques for LLM inference serving systems today are hybrid batching and disaggregated serving. A hybrid batch combines prefill and decode tokens of different requests in the same batch to improve resource utilization…

Due to the speed limitation of the conventional bit-chosen strategy in the existing weighted bit flipping algorithms, a high-speed LDPC decoder cannot be realized. To solve this problem, we propose a fast weighted bit flipping (FWBF)…