---
title: "From Power to Inference—Building a Distributed AI Compute Network | Aguasto"
description: "Connect physical capacity, server/runtime assumptions and completed inference work through a transparent conceptual measurement methodology."
canonical: "https://www.aguasto.com/learn/from-power-to-inference"
last-updated: "2026-10-12"
---

# From Power to Inference—Building a Distributed AI Compute Network | Aguasto

Canonical HTML: [From Power to Inference—Building a Distributed AI Compute Network](https://www.aguasto.com/learn/from-power-to-inference)

> Connect physical capacity, server/runtime assumptions and completed inference work through a transparent conceptual measurement methodology.

[Aguasto](https://www.aguasto.com/) [learn](https://www.aguasto.com/learn)  From Power to Inference—Building a Distributed AI Compute Network

[Resources](https://www.aguasto.com/resources) [GPU Library](https://www.aguasto.com/gpus) [Model Index](https://www.aguasto.com/models) [Inference Stack](https://www.aguasto.com/inference-stack) [Learn](https://www.aguasto.com/learn) [Insights](https://www.aguasto.com/insights) [Research](https://www.aguasto.com/research) [Engineering tools](https://www.aguasto.com/tools)

Aguasto / learn

## From Power to Inference—Building a Distributed AI Compute Network

Connect physical capacity, server/runtime assumptions and completed inference work through a transparent conceptual measurement methodology.

Original Aguasto conceptual illustration. Not manufacturer geometry, an operating Aguasto asset, or a measured benchmark.

By Aguasto Research · Published October 12, 2026 · Revision 1

Aguasto Research documents third-party hardware, models and software. References do not represent Aguasto inventory, evaluated deployments or available inference services.

### A conceptual infrastructure and routing architecture

Electrical service → Facility → Rack → Runtime → Model → API → Customer

- **Electrical service**Utility authorization and protection

- **Modular facility**Site works, heat rejection and approvals

- **GPU rack**Power, cooling and fabric integration

- **Serving software**Pinned runtime and hardware compatibility

- **Model deployment**License, weights, cache and evaluation

- **Inference API**Authentication, quotas and observability

- **Customer**Workload, latency and reliability requirements

A conceptual engineering chain for planned services. Each interface requires project-specific verification.

Conceptual distributed inference · Independent facilities and model replicas

**Enterprise request → Service routing**Choose an eligible region using latency, policy, health and available capacity.

#### Region A

Independent facility Local GPU racks & runtime Model replica & local cache

#### Region B

Independent facility Local GPU racks & runtime Model replica & local cache

#### Region C

Independent facility Local GPU racks & runtime Model replica & local cache

Geographic request routing does not join GPUs into one NVLink fabric. Failover needs compatible replicas, spare capacity and a defined data-handling policy.

### Start with a chain of measurable boundaries

A conceptual compute network connects electrical supply, facility distribution, cooling, racks, accelerators, serving engines and application requests. A capacity value at one boundary does not establish output at another. A proposed facility may have a utility discussion before it has commissioned electrical systems; a server may be installed before a model is loaded; a reachable endpoint may still miss a workload's latency objective.

For Aguasto's planned strategy, document each transition with a separate acceptance condition. The educational diagram should show dependencies and measurements, not owned facilities, authorized capacity or existing service regions. A complete development story needs the facility and the delivered-work records to agree.

### Distinguish IT energy from facility energy

DOE FEMP defines annual PUE as total facility energy divided by IT-equipment energy. Cooling and other infrastructure contribute to the facility boundary; water efficiency has a separate WUE definition. PUE does not measure model quality or tokens produced.

A simplified scenario can apply facility kW = IT kW × assumed PUE and kWh = kW × hours. For hypothetical 100 kW average IT load, PUE 1.3 and 24 hours, the result is 3,120 kWh of facility energy. This assumes constant load and a representative PUE for the period; it is not an audited annual PUE or a claimed Aguasto operating value.

[Cooling Water Efficiency Opportunities for Federal Data Centers — DOE FEMP (external source)](https://www.energy.gov/cmei/femp/cooling-water-efficiency-opportunities-federal-data-centers)

### Keep cooling and hardware assumptions explicit

The proposed rack worksheet should distinguish accelerator rating, server input, networking/storage load, rack input and facility input. Add idle, average workload and peak observations only when measured. Identify the cooling technology and heat-removal boundary, then verify it against the selected equipment and site engineering.

Do not convert a GPU thermal design rating into a whole-facility demand estimate without accounting for the rest of the system. For a future comparison using MLPerf power results, retain the full-system AC boundary and the accompanying workload: MLCommons says those measurements are valid for that benchmark, not a generic device or power-supply rating.

[MLPerf Inference: Datacenter — MLCommons (external source)](https://mlcommons.org/benchmarks/inference-datacenter/)

### Translate physical resources into completed work

The proposed serving record should attach the exact model, precision, engine, parallelism and load profile to actual completed output tokens. Report failures and latency objectives beside throughput. Compute cost per million completed output tokens as cost USD ÷ actual completed output tokens × 1,000,000, with a strictly positive denominator.

Define the included costs and interval: compute rental, energy, network, software, operations or a narrower subtotal. An electricity-only result must be labeled electricity cost, not total inference cost. Exclude theoretical peak tokens from the denominator. If no observed token count exists, leave the measured-cost result unavailable and keep a hypothetical scenario clearly separate.

### Distribute requests, while respecting the workload

A network of regional replicas is conceptually different from splitting one model across tightly coupled devices. The first can direct independent requests to eligible locations; the second depends on the selected parallelism and communication path. Define which form a deployment diagram depicts before choosing network or reliability assumptions.

In the proposed Aguasto architecture, evaluate user latency, eligible data locations, version consistency and spare capacity for each regional workload. Do not assume that distant sites form one training fabric or that moving a request moves its active cache. Geographic distribution should be justified by an application requirement and a tested routing/recovery policy.

### Build a delivery record, not a peak-capacity promise

Use a staged evidence record: authorized electrical service, commissioned facility systems, accepted rack configuration, loaded and verified model, representative serving run and monitored application behavior. Each stage should retain date, boundary and unresolved dependency. A later benchmark can then explain how infrastructure resources become useful responses.

Aguasto is developing this infrastructure thesis; it has not substantiated operating regions, GPU inventory or an inference API. This methodology allows a technically meaningful partner discussion now: which equipment, engineering interfaces and workload tests would be needed to validate the next step. It creates no procurement commitment, energy guarantee or operational service claim.

### Scope & limitations

- Conceptual planned architecture; no Aguasto operating facility, regions or token service is implied.

- Energy arithmetic assumes constant average IT load and representative period PUE.

- No token throughput is inferred from electrical capacity or theoretical GPU peaks.

### Continue the research

[NVIDIA H200 SXM](https://www.aguasto.com/gpus/h200) [NVIDIA B200 SXM](https://www.aguasto.com/gpus/b200) [NVIDIA GB200 NVL72](https://www.aguasto.com/gpus/gb200-nvl72) [NVIDIA GB300 NVL72](https://www.aguasto.com/gpus/gb300-nvl72) [AMD Instinct MI355X](https://www.aguasto.com/gpus/mi355x) [AMD Helios](https://www.aguasto.com/gpus/helios) [vLLM](https://www.aguasto.com/inference-stack/vllm) [SGLang](https://www.aguasto.com/inference-stack/sglang) [NVIDIA Dynamo](https://www.aguasto.com/inference-stack/dynamo) [Ray Serve](https://www.aguasto.com/inference-stack/ray-serve) [Kubernetes GPU orchestration — NVIDIA device plugin](https://www.aguasto.com/inference-stack/kubernetes) [The Aguasto modular thesis](https://www.aguasto.com/why-modular) [Potential OEM and strategic collaboration](https://www.aguasto.com/partners)

### Sources & verification

Reference revision 1 · Reviewed October 12, 2026. Manufacturer claims and documentation are attributed; Aguasto has not run the cited products in production.

- [Cooling Water Efficiency Opportunities for Federal Data Centers — DOE FEMP ↗](https://www.energy.gov/cmei/femp/cooling-water-efficiency-opportunities-federal-data-centers)

Annual facility-energy/IT-energy PUE definition; WUE has a separate water measurement boundary; Heat-removal pathway through cooling equipment. Publication: 2019-01-09. Verified: 2026-10-12.

- [MLPerf Inference: Datacenter — MLCommons ↗](https://mlcommons.org/benchmarks/inference-datacenter/)

Results include submitter, software, accelerator count and metadata; Power measured at full-system AC boundary. Publication: date not stated in the reviewed source. Verified: 2026-10-12.

### In this publication

[Start with a chain of measurable boundaries](https://www.aguasto.com/learn/from-power-to-inference#section-1) [Distinguish IT energy from facility energy](https://www.aguasto.com/learn/from-power-to-inference#section-2) [Keep cooling and hardware assumptions explicit](https://www.aguasto.com/learn/from-power-to-inference#section-3) [Translate physical resources into completed work](https://www.aguasto.com/learn/from-power-to-inference#section-4) [Distribute requests, while respecting the workload](https://www.aguasto.com/learn/from-power-to-inference#section-5) [Build a delivery record, not a peak-capacity promise](https://www.aguasto.com/learn/from-power-to-inference#section-6) [More learn ↗](https://www.aguasto.com/learn) [Source register ↓](https://www.aguasto.com/learn/from-power-to-inference#sources)

## Company navigation

- [Home](https://www.aguasto.com/)
- [Infrastructure](https://www.aguasto.com/infrastructure)
- [GPU Cloud](https://www.aguasto.com/gpu-cloud)
- [AI Inference](https://www.aguasto.com/ai-inference)
- [Development & Investment](https://www.aguasto.com/development)
- [Company](https://www.aguasto.com/company)
- [Contact](https://www.aguasto.com/contact)
- [Privacy](https://www.aguasto.com/privacy)
- [Resources](https://www.aguasto.com/resources)
- [GPU Library](https://www.aguasto.com/gpus)
- [Model Index](https://www.aguasto.com/models)
- [Inference Stack](https://www.aguasto.com/inference-stack)
- [Learn](https://www.aguasto.com/learn)
- [Insights](https://www.aguasto.com/insights)
- [Research](https://www.aguasto.com/research)
- [Industry cases](https://www.aguasto.com/research/cases)
- [Why Modular](https://www.aguasto.com/why-modular)
- [Partners](https://www.aguasto.com/partners)
- [GPU comparison](https://www.aguasto.com/gpus/compare)
- [Model comparison](https://www.aguasto.com/models/compare)
- [Engineering tools](https://www.aguasto.com/tools)
- [Development friction](https://www.aguasto.com/research/hyperscale-development-friction)
- [NVIDIA H100 SXM](https://www.aguasto.com/gpus/h100)
- [NVIDIA H200 SXM](https://www.aguasto.com/gpus/h200)
- [NVIDIA B200 SXM](https://www.aguasto.com/gpus/b200)
- [NVIDIA B300](https://www.aguasto.com/gpus/b300)
- [NVIDIA GB200 NVL72](https://www.aguasto.com/gpus/gb200-nvl72)
- [NVIDIA GB300 NVL72](https://www.aguasto.com/gpus/gb300-nvl72)
- [NVIDIA Vera Rubin NVL72](https://www.aguasto.com/gpus/vera-rubin-nvl72)
- [AMD Instinct MI300X](https://www.aguasto.com/gpus/mi300x)
- [AMD Instinct MI325X](https://www.aguasto.com/gpus/mi325x)
- [AMD Instinct MI355X](https://www.aguasto.com/gpus/mi355x)
- [AMD Instinct MI455X](https://www.aguasto.com/gpus/mi455x)
- [AMD Helios](https://www.aguasto.com/gpus/helios)
- [GLM-4.5](https://www.aguasto.com/models/glm-4-5)
- [Qwen3-235B-A22B](https://www.aguasto.com/models/qwen3-235b-a22b)
- [DeepSeek-R1](https://www.aguasto.com/models/deepseek-r1)
- [Llama 3.3 70B Instruct](https://www.aguasto.com/models/llama-3-3-70b-instruct)
- [Gemma 3 27B IT](https://www.aguasto.com/models/gemma-3-27b-it)
- [gpt-oss-120b](https://www.aguasto.com/models/gpt-oss-120b)
- [Kimi-K2-Instruct](https://www.aguasto.com/models/kimi-k2-instruct)
- [vLLM](https://www.aguasto.com/inference-stack/vllm)
- [SGLang](https://www.aguasto.com/inference-stack/sglang)
- [TensorRT-LLM](https://www.aguasto.com/inference-stack/tensorrt-llm)
- [NVIDIA Dynamo](https://www.aguasto.com/inference-stack/dynamo)
- [NVIDIA Triton Inference Server](https://www.aguasto.com/inference-stack/triton)
- [AMD ROCm](https://www.aguasto.com/inference-stack/rocm)
- [Ray Serve](https://www.aguasto.com/inference-stack/ray-serve)
- [Kubernetes GPU orchestration — NVIDIA device plugin](https://www.aguasto.com/inference-stack/kubernetes)
- [Model weights are only the beginning of the memory budget](https://www.aguasto.com/learn/model-weights-and-runtime-memory)
- [Why tokens per second is not enough to benchmark inference](https://www.aguasto.com/research/inference-benchmark-methodology)
- [Prefill, decode and the cost of separating them](https://www.aguasto.com/learn/prefill-decode-and-disaggregated-serving)
- [Choosing between vLLM, SGLang and TensorRT-LLM](https://www.aguasto.com/learn/choosing-an-inference-serving-framework)
- [From Power to Inference—Building a Distributed AI Compute Network](https://www.aguasto.com/learn/from-power-to-inference)
- [Dedicated compute and shared inference: compare the whole workload](https://www.aguasto.com/insights/dedicated-and-shared-inference-economics)
- [Distributed inference reliability begins with the failure boundary](https://www.aguasto.com/learn/distributed-inference-reliability)
- [Core Scientific: reading contracted, energized and billed capacity](https://www.aguasto.com/research/cases/core-scientific-capacity-disclosures)
- [Why Modular AI Infrastructure Matters Now](https://www.aguasto.com/research/why-modular-ai-infrastructure-matters-now)
- [Official LinkedIn](https://www.linkedin.com/company/aguasto)

This is a generated representation of the public HTML page. Diagrams are conceptual. GPU and inference services are planned and are not currently available to book or call. The contact page describes the available inquiry flow.