Build a Generative Workload Token and Power Cost Attribution Engine

Correlate per-request token usage with real-time accelerator power consumption. Attribute energy and hardware depreciation costs across internal teams and model architectures.

FinOps and Sustainability Lead

Ingest serving request logs alongside DCGM and Neuron power telemetry records.

Calculate Joules-per-token and watt-hour attribution across concurrent tenants.

Prompt hosted Claude to summarize cost attribution anomalies and carbon footprints.

Compile an auditable monthly billing and sustainability report for department heads.

Multi-tenant dashboard displaying energy consumption charts, Joules/token heatmaps, and cost allocation breakdowns.

Create synthetic time-aligned logs combining open-weight model request traces (token counts) and sampled power draw (Watts) metrics. Starter examples below are synthetic. They are not downloaded records.

NVIDIA DCGM exporter Extracts DCGM GPU power draw metrics (DCGM_FI_DEV_POWER_USAGE) to calculate precise watt-hour consumption per inference window.

pydantic-ai, anthropic-claude, mlflow. Guarantees mathematical schema consistency across energy measurements, token tallies, and currency conversions. Hosted Claude API for natural language variance reporting and sustainability insight drafting.

Submit runnable source, pinned dependencies, setup commands, a working interface, example outputs, and a recorded end-to-end demo. Include tests and an action log.

Calculates energy-per-token metrics across at least two concurrent tenant workloads.

Reconciles aggregate power draw against individual request attributions within 3% tolerance.

Produces verified FinOps cost summaries exportable as JSON.

```json [ { "input": { "tenant_id": "search-team", "window_hours": 1, "tokens_processed": 5000000, "avg_power_watts": 420, "kwh_rate_usd": 0.12, "node_depreciation_hourly_usd": 1.5 }, "expected_output": { "energy_consumed_kwh": 0.42, "energy_cost_usd": 0.05, "total_attributed_cost_usd": 1.55, "joules_per_token": 0.302, "efficiency_rating": "optimal" } }, { "input": { "tenant_id": "idle-team", "window_hours": 1, "tokens_processed": 0, "avg_power_watts": 110, "kwh_rate_usd": 0.12, "node_depreciation_hourly_usd": 1.5 }, "expected_output": { "energy_consumed_kwh": 0.11, "energy_cost_usd": 0.013, "total_attributed_cost_usd": 1.513, "joules_per_token": 0, "efficiency_rating": "idle_waste" } } ] ```

Calculates accounting figures only; does not manipulate power caps or server governor settings. Use mock external writes. Require human review before any real deployment.