Mind the Memory Gap: Unveiling GPU Bottlenecks in Large-Batch LLM Inference
- Pol G. Recasens
- Ferran Agullo
- et al.
- 2025
- CLOUD 2025
Publications
4 results for Josep Lluis Berral
Towards Pareto Optimal Throughput in Small Language Model Serving
- Pol G. Recasens
- Yue Zhu
- et al.
- 2024
- EuroMLSys 2024
Theta-Scan: Leveraging Behavior-Driven Forecasting for Vertical Auto-Scaling in Container Cloud
- Josep Lluis Berral
- David Buchaca
- et al.
- 2021
- CLOUD 2021
You only Run Once: Spark Auto-Tuning from a Single Run
- David Buchaca Prats
- Felipe Albuquerque Portella
- et al.
- 2020
- IEEE TNSM