SuperMarioYL

_{EN  ⇄  中文}

_{I work across AI agents, cloud-native AI and inference acceleration: Agent Loop / RSI, disaggregated P/D deployments, and tiered KV cache reuse.}

System architecture

_{The agent layer uses model services; the inference layer connects engines to tiered storage for KV cache reuse; the cloud-native layer provides routing, P/D deployment and compute resources.}

Capabilities

Tech stack

Parallel tracks

Selected work

• Bison — Enterprise GPU billing & multi-tenant platform
• Inference Cookbook — Inference frameworks, deep-dived
• Cloud Native Cookbook — Cloud-native engineering, deep-dived