> ## Documentation Index
> Fetch the complete documentation index at: https://docs.getimpala.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Further reading

> Impala's engineering writing on inference economics, kernels and expert parallelism.

**[Research](https://www.getimpala.ai/research)** — The engine and its measured results.

## Cost and utilization

**[Run It Hot](https://www.getimpala.ai/blog/run-it-hot)** — Why utilization, not electricity price, is the lever on cost per token.

## Workload shape

**[Nobody's Waiting: Common Use Cases for Async AI](https://www.getimpala.ai/blog/nobodys-waiting-common-use-cases-for-async-ai)** — The share of inference where no human is reading the output, and what that changes.

**[Inference for Agentic Workloads Is Different](https://www.getimpala.ai/blog/inference-for-agentic-workloads-is-different-heres-what-that-means-for-your-stack)** — Why agent traces break the assumptions interactive serving is built on.

## Engine internals

**[DBO, Kernel Crossover, and the Real Hardware Cliff](https://www.getimpala.ai/blog/wide-ep-dbo-deepep-hardware-cliff)** — Where kernel choice stops scaling and what replaces it.

**[Wide-EP failure modes, load balancing, and portability](https://www.getimpala.ai/blog/wide-ep-load-balancing-portability)** — Expert parallelism at fleet scale, and how it fails.

## Building the platform

**[IaC You Can Reason About](https://www.getimpala.ai/blog/iac-you-can-reason-about)** — Part 1 of the DevOps series.

**[What Full BYOC Actually Takes](https://www.getimpala.ai/blog/what-full-byoc-actually-takes)** — Part 2, on deploying into [your own cloud](/getting-started-infrastructure-setup).