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

Batch inference

Import into Desktop
Import version

Choose import version

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

Train/load a small numeric model, split versioned input values into three disjoint shards, execute real inference in parallel, validate that the merged indices have no gaps or duplicates, and publish predictions as JSON Lines.

Public experiment
IMMUTABLE WORKFLOW VERSION

v1 / Official showcase: measured homeserver execution using a public immutable image

YAML

Workflow DAG

Loading workflow v1…

Code

Loading workflow…

Changes

Compare against

Choose compare against

Empty → v1

Loading changes…

SHA-256 6c8c2cdb03523a399248da483b0e64900648600b99a6ffdd03a89e90686b9ca9