AEGIS: Runtime-Guided GPU Collocation for Multi-Tenant Deep Learning Training

arXiv:2508.19073 · cs.DC, cs.LG, cs.PF · Submitted 2025-08-26 · Read on arXiv

cs.DC, cs.LG, cs.PF

Submitted: 2025-08-26

Updated: 2026-10-06

Code: https://github.com/ehsanyousefzadehasl/dl-trace-mapper

Terminology

• Energy Efficiency — 1× in this paper · explained in 3 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Trace — 1× in this paper · explained in 2 episodes

Sources

• Deep Learning Workload Scheduling in GPU Datacenters: Taxonomy, Challenges and Vision

Related papers

• iScheduler: Reinforcement Learning-Driven Continual Optimization for Large-Scale Resource Investment Problems
• SAMM: Sharded Automated Market Maker
• InferScale: GPU-Native KV Injection for Personalized LLM Serving
• Vigil: Accountable Liveness against Selective Silence
• Steelhead: Interleaving Partially Synchronous and Asynchronous Commit Rules on a Shared DAG
• Democratizing MoE inference on commodity GPUs with CoMoE