[{"content":"I\u0026rsquo;m a Go / Kubernetes engineer (7 years) working on LLM inference control-plane and scheduling for a platform that runs across heterogeneous domestic accelerators — Ascend, Cambricon, Hygon, Moore Threads, Kunlunxin — alongside NVIDIA.\nMost public LLM-inference benchmarks only cover NVIDIA. I happen to have hands-on access to a rack of domestic accelerators, so I publish the head-to-head numbers almost no one else can — same model, same load, measured the same way — plus the routing, KV-cache, and cost trade-offs behind them.\nMy rule: every number ships with the exact command to reproduce it. If I can\u0026rsquo;t show you how to reproduce it, I don\u0026rsquo;t publish it.\nGitHub: Wangmin362 ","permalink":"https://wangmin362.github.io/en/about/","summary":"about","title":"About"}]