paper-with-me

Papers

An Architecture for Accelerated Large-Scale Inference of Transformer-Based Language Models

2021-06-01 · NAACL 2021 4 · Amir Ganiev, Colton Chapin, Anderson de Andrade, Chen Liu

This work demonstrates the development process of a machine learning architecture for inference that can scale to a large volume of requests. We used a BERT model that was fine-tuned for emotion analysis, returning a probability distribution of emotions given a paragraph. The model was deployed as a gRPC service on Kubernetes. Apache Spark was used to perform inference in batches by calling the service. We encountered some performance and concurrency challenges and created solutions to achieve faster running time. Starting with 200 successful inference requests per minute, we were able to achieve as high as 18 thousand successful requests per minute with the same batch job resource allocation. As a result, we successfully stored emotion probabilities for 95 million paragraphs within 96 hours.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Emotion Recognition

Methods 이 논문이 사용한 방법론

Golden Queue Managers 설명 없음
Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Adam 설명 없음
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.
Residual Connection 설명 없음
WordPiece 설명 없음

Similar Papers 제목 키워드 기반

LLMCache: Layer-Wise Caching Strategies for Accelerated Reuse in Transformer Inference

2025-12-18 · Harsh Vardhan Bansal arxiv

Transformer-based language models have achieved remarkable performance across a wide range of tasks, yet their high inference latency poses a significant challenge for real-timeand large-scale deployment. While existing …

Semantic Similarity

Magnetic Resonance Image Processing Transformer for General Accelerated Image Reconstruction

2024-05-23 · Guoyao Shen, Mengyu Li, Stephan Anderson, Chad W. Farris 외

Recent advancements in deep learning have enabled the development of generalizable models that achieve state-of-the-art performance across various imaging tasks. Vision Transformer (ViT)-based architectures, in particula…

AnatomyDeep LearningFew-Shot LearningImage Reconstruction+4

FaRAccel: FPGA-Accelerated Defense Architecture for Efficient Bit-Flip Attack Resilience in Transformer Models

2025-10-28 · Najmeh Nazari, Banafsheh Saber Latibari, Elahe Hosseini, Fatemeh Movafagh 외 arxiv

Forget and Rewire (FaR) methodology has demonstrated strong resilience against Bit-Flip Attacks (BFAs) on Transformer-based models by obfuscating critical parameters through dynamic rewiring of linear layers. However, th…

MSG-Transformer: Exchanging Local Spatial Information by Manipulating Messenger Tokens

2021-05-31 · CVPR 2022 1 · Jiemin Fang, Lingxi Xie, Xinggang Wang, Xiaopeng Zhang 외

Transformers have offered a new methodology of designing neural networks for visual recognition. Compared to convolutional networks, Transformers enjoy the ability of referring to global features at each stage, yet the a…

CPUGPUimage-classificationImage Classification+2

HUMUS-Net: Hybrid unrolled multi-scale network architecture for accelerated MRI reconstruction

2022-03-15 · Zalan Fabian, Berk Tınaz, Mahdi Soltanolkotabi

In accelerated MRI reconstruction, the anatomy of a patient is recovered from a set of under-sampled and noisy measurements. Deep learning approaches have been proven to be successful in solving this ill-posed inverse pr…

AnatomyMRI Reconstruction