SMART-MIG: A Learning Framework for Scalable and Energy-Efficient GPU Scheduling
- Wenqing Yu
- Neel Karia
- et al.
- 2026
- IPDPS 2026
Conference paper
Publications
40 results for Olivier Tardieu
Toward Efficient Orchestration for GenAI Workloads in Modern Container Clouds
- Jose Santos
- Chen Wang
- et al.
- 2026
- IEEE Communications Magazine
PaperA Data-driven ML Approach for Maximizing Performance in LLM-Adapter Serving
- Ferran Agullo Lopez
- Joan Oliveras Torra
- et al.
- 2025
- NeurIPS 2025
Workshop paperMind the Memory Gap: Unveiling GPU Bottlenecks in Large-Batch LLM Inference
- Pol G. Recasens
- Ferran Agullo
- et al.
- 2025
- CLOUD 2025
Conference paperThe Bottlenecks of AI: Challenges for Embedded and Real-Time Research in a Data-Centric Age
- Tarek Abdelzaher
- Yigong Hu
- et al.
- 2025
- Real-Time Systems
PaperEvaluating the Network Effects of Orchestration Strategies for AI Workloads in Modern Data Centers
- José Santos
- Pavlos Maniotis
- et al.
- 2025
- NetSoft 2025
Conference paperEnergy Efficient Scheduling of AI/ML Workloads on Multi-Instance GPUs with Dynamic Repartitioning
- Ellie Lipe
- Neel Karia
- et al.
- 2025
- IPDPSW 2025
Conference paperEnergy Efficient Scheduling of AI/ML Workloads on Multi Instance Gpus with Dynamic Repartitioning
- Ellie Lipe
- Neel Karia
- et al.
- 2025
- CCGrid 2025
Conference paperBuild, Operate, and Use a multi-tenant AI cluster based entirely on open source
- Claudia Misale
- Olivier Tardieu
- et al.
- 2025
- KubeCon EU 2025
TalkIncremental GPU Slicing in Action
- Abhishek Malvankar
- Olivier Tardieu
- 2024
- CNCF-hosted Co-located Events North America 2024
Talk