Some questions about torch.compile

[wyzqwq]

Hi Pytorch team,

The article PyTorch + vLLM = – PyTorch shows 1.05x–1.9x speedups with torch.compile for models like Llama4/Qwen3/Gemma3. To better understand:

1. What benchmark setup (hardware, input shape) was used?
2. Was this measured by comparing vLLM with vs. without torch.compile enabled?
3. Could you share a reference script/command for reproducing these tests?

Thanks for your insights! This will greatly help the community validate the optimizations.