MISO: Exploiting Multi-Instance GPU Capability on Multi-Tenant GPU Clusters
Main Authors: | Li, Baolin, Patel, Tirthak, Samsi, Siddharth, Gadepally, Vijay, Tiwari, Devesh |
---|---|
Other Authors: | Lincoln Laboratory |
Format: | Article |
Language: | English |
Published: |
ACM|ACM Symposium on Cloud Computing
2023
|
Online Access: | https://hdl.handle.net/1721.1/147687 |
Similar Items
-
Sustainable Supercomputing for AI: GPU Power Capping at HPC Scale
by: Zhao, Dan, et al.
Published: (2023) -
Ribbon: Cost-Effective and QoS-Aware Deep Learning Model Inference using a Diverse Pool of Cloud Computing Instances
by: Li, Baolin, et al.
Published: (2022) -
Kairos: Building Cost-Efficient Machine Learning Inference Systems with Heterogeneous Cloud Resources
by: Li, Baolin, et al.
Published: (2023) -
Clover: Toward Sustainable AI with Carbon-Aware Machine Learning Inference Service
by: Li, Baolin, et al.
Published: (2023) -
BLISS: Auto-tuning Complex Applications Using A Pool of Diverse Lightweight Learning Models
by: Roy, Rohan Basu, et al.
Published: (2022)