# gpu-perf-tune

> gpu-perf-tune — cfregly-gpu-perf-tune. Use this tool when you need to optimize and benchmark GPU performance for inference workloads, and analyze performance bottlenecks to improve overall system efficiency. It provides detailed profiling and reporting capabilities to identify areas for optimization, taking in GPU performance data as input and outputting actionable insights and recommendations. Ideal for use cases where maximizing GPU utilization and minimizing latency are critical, such as AI model deployment and machine learning workflows.

Canonical page: https://skillsregistry.net/skills/cfregly-gpu-perf-tune  
JSON: https://api.skillsregistry.net/v1/skills/cfregly-gpu-perf-tune

## Description

Agent Skills and an MCP server for GPU performance profiling, benchmarking, optimization, and reporting, with an inference focus.

## Trust

- **Trust score (0–1):** 0.88
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## 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/cfregly/gpu-perf-tune)

## 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": "cfregly-gpu-perf-tune"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/cfregly-gpu-perf-tune` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/cfregly-gpu-perf-tune/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