triton.testing.do_bench_cudagraph

triton.testing.do_bench_cudagraph(fn, rep=20, grad_to_none=None, quantiles=None, return_mode='mean')

Benchmark the runtime of the provided function.

参数:

• fn (Callable) -- Function to benchmark

• rep (int) -- Repetition time (in ms)

• grad_to_none (torch.tensor, optional) -- Reset the gradient of the provided tensor to None

• return_mode (str) -- The statistical measure to return. Options are "min", "max", "mean", "median", or "all". Default is "mean".