Home / Skills / serving-llms-on-epyc
serving-llms-on-epyc
amd/skillsSkill
Serves an LLM on a supported AMD EPYC server CPU using vLLM with zentorch, in
Why this score
This repo hosts 10 skills, so its 423 stars are split between them (about 42 each) for scoring.
Popularity score: 64/100 from public GitHub signals only. It shows how widely used and maintained this is, not how well it works. Not included yet: the fake-star check. The security scan is shown separately and doesn't change the score. How we rank
Security
Scanned Oct 21, 2026 at commit c729955ac862, with Cisco's open-source skill-scanner.
What its code does:
- Reads environment variables and sends network requests with them API clients do this to send your key to the service. Check which service it talks to.
- Runs shell commands Common for dev tools. Read the commands it runs.scripts/cpu_tune.py:53, scripts/detect.py:43, scripts/validate.py:61
- Makes network requestsSKILL.md, scripts/check_model.py:65, scripts/estimate_memory.py:33 and 1 more
Web addresses in its code:
- huggingface.coscripts/check_model.py:40
- raw.githubusercontent.comscripts/check_model.py:41
These are the sites named in the code, so it's where your data could go. It isn't a complete list: code can build addresses while it runs, and a few of these may be links rather than calls. Whatever you send also goes to the AI model you use.
A scan lists patterns in the code. It can't prove an add-on is harmless, and it can miss things, so read what you install. How we scan
Alternatives
Other makers' add-ons that do the same job, next to this one.
| Name | Score | Stars | Context | Updated |
|---|---|---|---|---|
| This oneserving-llms-on-epyc amd/skills · Skill | 64 | ★ 423 | ≈25 always | 16d ago |
| nat-mcp-and-serving NVIDIA/NeMo-Agent-Toolkit · Skill Both about serving | 75 | ★ 2.7k | ≈46 always | 17d ago |
| hf-cloud-serving-image-selection huggingface/skills · Skill Both about serving and serve | 79 | ★ 11k | ≈158 always | 27d ago |