# LLM Torch Profiler Analysis

> Unified LLM torch-profiler triage skill for sglang, vllm, TensorRT-LLM, and TokenSpeed. Use it to inspect an existing trace.json(.gz) or profile directory, or to drive live profiling against a running server when supported and return one three-table report with kernel, overlap-opportunity, and fuse-pattern tables.

## Facts
- Page: https://tashan.sh/capability/skill-bbuf-llm-torch-profiler-analysis
- tashan id: skill:BBuf/llm-torch-profiler-analysis
- Source: https://github.com/BBuf/AI-Infra-Auto-Driven-SKILLS
- Type: skill
- Category: devtools
- tashan score: not scored (catalogued only — too little public evidence)
- Adoption: 9.0
- Upkeep: 100.0
- Freshness: 100.0
- Evidence coverage: 84% of the inputs this score can use
- Health: active
- Instruction depth: not yet graded
- Official: no

## Install

```sh
cp -r llm-torch-profiler-analysis ~/.claude/skills/
```

## Security audit
Not scanned. We audit npm-published capabilities; this one has no npm package we can resolve, or has not reached the queue. This is not a clean bill of health.

---
Measured 2026-08-25 by tashan (https://tashan.sh) from public evidence. Scorer s5.