(github.com)

486 points dbreunig | 1 comments | 16 Oct 24 19:44 UTC | HN request time: 0.217s | source

1. woadwarrior01 ◴[17 Oct 24 07:36 UTC] No.41867284[source]▶

IMO, benchmarking accelerator hardware with onnxruntime is like benchmarking a CPU with a Python script.

> We've seen similar performance results to those shown here using the Qualcomm QNN SDK directly.

Why not include those results?

AI PCs Aren't Good at AI: The CPU Beats the NPU