Processing time comparison between
onnxruntime and
onnx‑light‑cpu
(onnx‑light's reference evaluator with the SIMD-accelerated CPU kernels
registered) on the benchmark
examples
shipped by onnx‑light‑cpu. Each example sweeps an
operator over a range of input sizes; numpy and
onnx‑light's own un-accelerated reference kernel are shown
as baselines. Every measurement runs
3 warm-up calls (not timed) and keeps the
median of 10 timed repetitions.
speed-up (cpu) = onnxruntime /
onnx‑light‑cpu: values > 1 mean
onnx‑light‑cpu is faster than onnxruntime. Select an operator
summary row to expand its detailed measurements.