Building py-kvcache: A Performance Characterization of External KV Caching for vLLM with NVMe SSDs

arXiv:2609.11744 · cs.DC, cs.LG · Submitted 2026-09-10 · Read on arXiv

cs.DC, cs.LG

Submitted: 2026-09-10

Updated: 2026-09-10

Code: https://github.com/atlarge-research/py-kvcache

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Trace — 2× in this paper · explained in 2 episodes
• Benchmark — 1× in this paper · explained in 2 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
• Pushing CPU Speech Synthesis to the Wall: Extreme Inference Tuning under Serverless Architecture and Billing