# DIO

> DIO — nisaral-dio. Use this tool when you need to optimize large language model (LLM) performance and latency. DIO solves routing and admission control problems for multiple LLM backends, including OpenAI and Ollama, by learning latency online and ensuring SLO-aware admission. It takes in vLLM, SGLang, TGI, and Ollama inputs and outputs optimized routing decisions, making it ideal for use cases requiring low-latency and high-performance LLM processing.

Canonical page: https://skillsregistry.net/skills/nisaral-dio  
JSON: https://api.skillsregistry.net/v1/skills/nisaral-dio

## Description

Drop-in OpenAI- and Ollama-compatible LLM gateway that learns each backend's latency online and routes vLLM / SGLang / TGI / Ollama with SLO-aware admission. No engine patches.

## Trust

- **Trust score (0–1):** 0.86
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** Apache-2.0
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/nisaral/DIO)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "nisaral-dio"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/nisaral-dio` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/nisaral-dio/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt