A Grid Based Architecture for High-Performance NLP
Baden Hughes, Steven Bird
Abstract
We describe the design and early implementation of an extensible, component-based software architecture for natural language engineering applications which interfaces with high performance distributed computing services. The architecture leverages existing linguistic resource description and discovery mechanisms based on metadata descriptions, combining these in a compatible fashion with other software definition abstractions. Within this architecture, application design is highly flexible, allowing disparate components to be combined to suit the overall application functionality, and formally described independently of processing concerns. An application specification language provides abstraction from the programming environment and allows ease of interface with high performance computational grids via a broker.
Create a lesson
Related papers
PixelFlow: Token-Level Workload Management for Efficient Distributed DiT Serving
Zhexiang Zhang, Minchen Yu, Yifan Sun et al.
A Kubernetes-Native Request Router for Quality-Aware Inference Serving in the Computing Continuum
Ignjat Karanovic, Pantelis A. Frangoudis, Ivan Čilić et al.
Accelerating Sharded Data Parallelism at Scale with Federated Learning
Gianluca Mittone, Marco Aldinucci
Distributed Edge Inference: an Experimental Study on Multiview Detection
Gianluca Mittone, Giulio Malenza, Marco Aldinucci et al.
P-GADMM: Parallel Group-Based ADMM for Asynchronous Optimization in Heterogeneous Edge Networks
Gaiguo Wei, Qingying Zhang, Heqiang Wang et al.
VERA: Reinforcement Learning for Dynamic Memory Scaling of HPC Workloads in Kubernetes
Ade Pramono, Jie Ren, Ivy Peng