# genpark-edge-inference-latency-telemetry-skill

> genpark-edge-inference-latency-telemetry-skill — alpha-park-genpark-edge-inference-latency-telemetry-skill. Use this tool when you need to measure and optimize the performance of large language models (LLMs) on edge devices or on-device inference, solving problems of latency and throughput analysis. It calculates key metrics such as time-to-first-token (TTFT), time-to-post-processing-output (TPOT), tokens per second, and jitter distributions. This skill is ideal for use cases requiring high-precision profiling and optimization of LLM inference latency and throughput.

Canonical page: https://skillsregistry.net/skills/alpha-park-genpark-edge-inference-latency-telemetry-skill  
JSON: https://api.skillsregistry.net/v1/skills/alpha-park-genpark-edge-inference-latency-telemetry-skill

## Description

High-precision edge and on-device LLM inference profiler calculating TTFT, TPOT, tokens/second throughput, and percentile jitter distributions (P50/P90/P99).

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

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

## Source

- **Source listing:** [GitHub](https://github.com/Alpha-Park/genpark-edge-inference-latency-telemetry-skill)

## 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": "alpha-park-genpark-edge-inference-latency-telemetry-skill"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/alpha-park-genpark-edge-inference-latency-telemetry-skill` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/alpha-park-genpark-edge-inference-latency-telemetry-skill/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