Inference benchmark

Compare one frozen model and input set across CPU, GPU, and edge targets.

freeze model and inputs→benchmark CPUbenchmark GPUbenchmark edge→normalize measurements→compare cost and latency

Inference benchmark

Activity responsibilities

Activity	Responsibility
freeze-model-and-inputs	Execute the freeze model and inputs stage and publish its declared outputs for downstream activities.
benchmark-cpu	Execute the benchmark CPU stage and publish its declared outputs for downstream activities.
benchmark-gpu	Execute the benchmark GPU stage and publish its declared outputs for downstream activities.
benchmark-edge	Execute the benchmark edge stage and publish its declared outputs for downstream activities.
normalize-measurements	Execute the normalize measurements 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

• Raw traces
• Normalized metrics
• Comparison

Provenance to preserve

• Hardware and runtime
• Warm-up policy
• Batch and concurrency

Runnable example

This is the complete checked-in bundle for this pattern. Download the environment, scope, topology, workflow, input, container recipe, runner, and validation contract from this page before executing it.

Read setup instructions ↓Environment YAML ↓Execution scope YAML ↓Network topology YAML ↓Workflow YAML ↓Input data ↓Container recipe ↓Run the workflow ↓Validate outputs ↓Expected output manifest ↓

Verified local execution

These captures and the output manifest were produced by the fixture's local Docker run and validator. They are published with the same bundle as the runnable files.

Workflow evidence

Execution evidence

Output evidence

Open verified output manifest ↓

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.