[renonce]

From the first paragraph:

> enabling precise file identification within milliseconds, even when running on a CPU.

Maybe your old-fashioned implementations were detecting in microseconds?

[stevepike]

Yeah I saw that, but that could cover a pretty wide range and it's not clear to me whether that relies on preloading a model.

[ryanjshaw]

> At inference time Magika uses Onnx as an inference engine to ensure files are identified in a matter of milliseconds, almost as fast as a non-AI tool even on CPU.