AI Agent Skills

Benchmarks LLM inference and drives GPU kernel optimization with Magpie. Use when the user wants to benchmark vLLM, SGLang, or Atom; capture torch traces; post-process i…

Run an arbitrary Hugging Face safetensors model on an Intel GPU using **upstream PyTorch** (>= 2.8) with the built-in `torch.xpu` device. Covers loading from the Hub, pi…