AkôFlowHub
Explore
Back to Research
akoflow / machine-learning-inference-benchmark

Inference benchmark

Import into Desktop
Import version

Choose import version

akoflow::o/akoflow/machine-learning-inference-benchmark:v1

Measure actual local CPU inference with three batching profiles and verify identical predictions. The branches named CPU, GPU, and edge use CPU fallback batching in the portable profile; no GPU/edge hardware performance or cloud billing is claimed.

Public experiment

Experiment results

All published executions across workflow versions. Open an execution to inspect its recorded data.

Source workflow

Choose source workflow

Loading result visualizations…