NUDIF: A Non-Uniform Deployment Framework for Distributed Inference in Heterogeneous Edge Clusters
Distributed inference in resource-constrained heterogeneous edge clusters is fundamentally limited by disparities in device capabilities and load imbalance issues. Existing methods predominantly focus on optimizing single-pipeline allocation schemes for partitioned sub-models. However, such approach...
Saved in:
| Main Authors: | Peng Li, Chen Qing, Hao Liu |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-04-01
|
| Series: | Future Internet |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1999-5903/17/4/168 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
A Matching Game for LLM Layer Deployment in Heterogeneous Edge Networks
by: Benedetta Picano, et al.
Published: (2025-01-01) -
Private Collaborative Edge Inference via Over-the-Air Computation
by: Selim F. Yilmaz, et al.
Published: (2025-01-01) -
Hive: A secure, scalable framework for distributed Ollama inference
by: Domen Vake, et al.
Published: (2025-05-01) -
A Remedy for Heterogeneous Data: Clustered Federated Learning with Gradient Trajectory
by: Ruiqi Liu, et al.
Published: (2024-12-01) -
PARAMETER ESTIMATION OF LOGNORMAL AND PARETO TYPE I DISTRIBUTIONS USING FREQUENTIST AND BAYESIAN INFERENCES
by: Jenisha Then, et al.
Published: (2025-01-01)