Mind the Memory Gap: Unveiling GPU Bottlenecks in Large-Batch LLM Inference
- Pol G. Recasens
- Ferran Agullo
- et al.
- 2025
- CLOUD 2025
Publications
34 results for Olivier Tardieu
The 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
Build, Operate, and Use a multi-tenant AI cluster based entirely on open source
- Claudia Misale
- Olivier Tardieu
- et al.
- 2025
- KubeCon EU 2025
Incremental GPU Slicing in Action
- Abhishek Malvankar
- Olivier Tardieu
- 2024
- CNCF-hosted Co-located Events North America 2024
Caspian: A Carbon-aware Workload Scheduler in Multi-Cluster Kubernetes Environments
- Tayebeh Bahreini
- Asser Tantawi
- et al.
- 2024
- MASCOTS 2024
GPU OPTIMIZATIONS FOR EFFICIENT AND COST-EFFECTIVE ACCESS TO DIVERSE LARGE LANGUAGE MODELS IN RESEARCH CLUSTER
- Chen Wang
- Yue Zhu
- et al.
- 2024
- MLSys 2024
Towards Pareto Optimal Throughput in Small Language Model Serving
- Pol G. Recasens
- Yue Zhu
- et al.
- 2024
- EuroSys 2024
Towards Pareto Optimal Throughput in Small Language Model Serving
- Pol G. Recasens
- Yue Zhu
- et al.
- 2024
- EuroMLSys 2024
Unleashing the Power of DRA (Dynamic Resource Allocation) for Just-in-Time GPU Slicing
- Abhishek Malvankar
- Olivier Tardieu
- 2024
- KubeCon EU 2024
Training Foundation Model Workloads on Kubernetes at Scale With MCAD
- Olivier Tardieu
- Abhishek Malvankar
- 2023
- K8SAIHPCDAY 2023