arle-upstream-runtime-scan

Use this skill when ckl asks to ground an ARLE serving/runtime, model-path, benchmark, capacity, Qwen3.5/DeepSeek, scheduler, paged_kv, MLX, autograd, or OPD decision in upstream SGLang/vLLM/TensorRT-LLM evidence before changing local code. It distills BBuf AI-Infra Auto Driven SKILLS into an ARLE-specific source-survey workflow without symlinking or vendoring those repositories.