English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Multi-Instance GPU (MIG) is a new feature introduced by NVIDIA A100 GPUs thatpartitions one physical GPU into multiple GPU instances. With MIG, A100 can bethe most cost-efficient GPU ever for serving Deep Neural Networks (DNNs).However, discovering the most efficient GPU partitions is challenging. Theunderlying problem is NP-hard; moreover, it is a new abstract problem, which wedefine as the Reconfigurable Machine Scheduling Problem (RMS). This paperstudies serving DNNs with MIG, a new case of RMS. We further propose asolution, MIG-serving. MIG- serving is an algorithm pipeline that blends avariety of newly designed algorithms and customized classic algorithms,including a heuristic greedy algorithm, Genetic Algorithm (GA), and Monte CarloTree Search algorithm (MCTS). We implement MIG-serving on Kubernetes. Ourexperiments show that compared to using A100 as-is, MIG-serving can save up to40% of GPUs while providing the same throughput.

Serving DNN Models with Multi-Instance GPUs: A Case of the Reconfigurable Machine Scheduling Problem