Coral: Cost-Efficient Multi-LLM Serving over Heterogeneous Cloud GPUs

arXiv:2605.04357 · cs.DC, cs.AI, cs.CL, cs.LG · Submitted 2026-05-05 · Read on arXiv

cs.DC, cs.AI, cs.CL, cs.LG

Submitted: 2026-05-05

Updated: 2026-10-17

Terminology

• Harness — 1× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 8 episodes

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
• Lightweight Scheduling Policies for Continuously Batched LLM Serving Across GPU Architectures