Inference benchmark
Compare one frozen model and input set across CPU, GPU, and edge targets.
Import this workflow from AkôFlow Hub
Open the public README and measured execution results. The Hub includes the execution capture, activity metrics, logs and version history. Reading public results does not require an account.
In Desktop, choose Create workflow → Import from Hub and paste this version-specific URI:
akoflow://hub/publications/a0dde05c-5f4e-425a-94b7-6c6436e3cee7/versions/1
Download the exact workflow YAML (v1). Configure the runtime prerequisites below before planning and executing it.
Run this example locally
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.
Install Go and Python 3.12 or newer.
git clone https://github.com/UFFeScience/akoflow-examples.git &&
cd akoflow-examples &&
git checkout --detach d890c3171e3661890305b763b8fc3ede48bb61b4 &&
cd machine-learning/inference-benchmark &&
./prepare.sh &&
./run.sh
Run the block from the directory where you keep your repositories. If you already cloned the repository, enter this example's directory and run ./prepare.sh && ./run.sh.
Preparation downloads the Go module and any declared Python packages once. The workload then runs locally with offline input data. Every meaningful step is a separate process; independent activities run in parallel after their dependencies complete.
Read outputs/manifest.json for the generated artifacts, outputs/dag-validation.json for dependency waves, and outputs/stage-<activity>.json for each activity's observed result. A failed stage stops the run and prevents a successful final manifest.
Expected outputs: benchmark.csv, report.html.
Run the same activities in Desktop
Start your local AkôFlow daemon with Docker available and configure AKOFLOW_API_TOKEN in your shell. From this example's directory, run:
go run ../../tools/daemon-local -root ../.. -example machine-learning/inference-benchmark
This command validates the daemon connection, builds the declared image, registers the local environment and workflow, and submits a real run. The daemon owns execution and file transfers. Open the printed run ID in Desktop to inspect each activity.
Activity responsibilities
| Activity | Responsibility |
|---|---|
freeze-inputs | Execute the freeze-inputs stage and publish its declared outputs for downstream activities. |
cpu | Execute the cpu stage and publish its declared outputs for downstream activities. |
gpu | Execute the gpu stage and publish its declared outputs for downstream activities. |
edge | Execute the edge stage and publish its declared outputs for downstream activities. |
normalize | Execute the normalize stage and publish its declared outputs for downstream activities. |
compare-cost-and-latency | Execute the compare-cost-and-latency stage and publish its declared outputs for downstream activities. |
Inputs
- Model and inputs
- Benchmark protocol
- Target scopes
Outputs
- benchmark.csv
- report.html
Provenance to preserve
- Hardware and runtime
- Warm-up policy
- Batch and concurrency
Source bundle
The executable workflow and its implementation files are maintained in the separate AkôFlow examples repository. The documentation intentionally keeps code, container recipes, generators, and validation scripts out of the narrative page.
Open the complete source bundle ↗Execution evidence
Verified on local Docker: 6/6 activities completed. These captures belong to run showcase-inference-benchmark-local-7d8f10cfda-run-20261020t191004.383307000.
Read the daemon execution record · Local output manifest
Each stage also ran through the standalone local command. Read the dependency and artifact validation.
freeze-inputs
After: workflow start.
cpu
After: freeze-inputs.
gpu
After: freeze-inputs.
edge
After: freeze-inputs.
normalize
After: cpu, gpu, edge.
compare-cost-and-latency
After: normalize.
Execution considerations
Separate cold-start from steady-state measurements and preserve the execution scope for every observation.
AkôFlow boundary: the engine schedules, deploys, executes, transfers data, and records evidence. The ML or agent framework remains an implementation choice inside each activity.