← All skills
serving-llms-vllm
70 / 100 · Review before installing
Check before installing. Some of what it can do is expected: a devops skill usually runs commands, installs tools and uses cloud credentials.
By artubss/SKILLS-CLAUDE-CODE (GitHub) · devops · 11 stars · scanned at commit ac67ed8
Serve LLMs com alta throughput usando PagedAttention do vLLM e continuous batching. Use ao fazer deploy de APIs LLM em produção, otimizar latência/throughput de inferência, ou servir modelos com memória GPU limitada. Suporta endpoints compatíveis com OpenAI, quantização (GPTQ/AWQ/FP8) e tensor parallelism.
Works with any agent that supports SKILL.md skills.
What this skill can do
Downloads and installs other software
The author does not mention this. Expected for a devops skill.
Found in 8 places.
Show 5 more
Runs commands on your computer
The author does not mention this. Expected for a devops skill.
Found in 15 places.
Show 12 more
- skills/skills/ai-research/inference-serving-vllm/SKILL.md, line 97
pip install locust - skills/skills/ai-research/inference-serving-vllm/SKILL.md, line 110
curl http://localhost:9090/metrics | grep vllm - skills/skills/ai-research/inference-serving-vllm/SKILL.md, line 124
docker run --gpus all -p 8000:8000 \ - skills/skills/ai-research/inference-serving-vllm/SKILL.md, line 250
vllm serve TheBloke/Llama-2-70B-AWQ \ - skills/skills/ai-research/inference-serving-vllm/SKILL.md, line 288
vllm serve MODEL \ - skills/skills/ai-research/inference-serving-vllm/SKILL.md, line 295
vllm serve MODEL --quantization awq - skills/skills/ai-research/inference-serving-vllm/SKILL.md, line 302
vllm serve MODEL --enable-prefix-caching - skills/skills/ai-research/inference-serving-vllm/SKILL.md, line 307
vllm serve MODEL --enable-chunked-prefill - skills/skills/ai-research/inference-serving-vllm/SKILL.md, line 314
vllm serve MODEL --trust-remote-code - skills/skills/ai-research/inference-serving-vllm/SKILL.md, line 321
vllm serve MODEL --max-num-seqs 512 - skills/skills/ai-research/inference-serving-vllm/SKILL.md, line 330
vllm serve MODEL --tensor-parallel-size 4 # Não 3 - skills/skills/ai-research/inference-serving-vllm/SKILL.md, line 335
vllm serve MODEL --speculative-model DRAFT_MODEL
Can call paid AI services billed to you
This is disclosed by the author in the skill's SKILL.md or README.
Found in 3 places.
Sends data to these websites: api.openai.com
The author does not mention this. Expected for a devops skill.
Found in 14 places.
Show 11 more
- skills/skills/ai-research/inference-serving-vllm/references/quantization.md, line 58
from openai import OpenAI - skills/skills/ai-research/inference-serving-vllm/references/server-deployment.md, line 225
curl http://localhost:8000/health - skills/skills/ai-research/inference-serving-vllm/references/server-deployment.md, line 232
until curl -f http://localhost:8000/health; do - skills/skills/ai-research/inference-serving-vllm/references/troubleshooting.md, line 207
curl http://localhost:8000/health - skills/skills/ai-research/inference-serving-vllm/references/troubleshooting.md, line 231
from openai import OpenAI - skills/skills/ai-research/inference-serving-vllm/references/troubleshooting.md, line 251
session = requests.Session() - skills/skills/ai-research/inference-serving-vllm/references/troubleshooting.md, line 377
curl http://localhost:9090/metrics - skills/skills/ai-research/inference-serving-vllm/references/troubleshooting.md, line 380
curl http://localhost:9090/metrics | grep vllm_time_to_first_token - skills/skills/ai-research/inference-serving-vllm/references/troubleshooting.md, line 394
curl http://localhost:8000/health - skills/skills/ai-research/inference-serving-vllm/references/troubleshooting.md, line 397
curl http://localhost:8000/v1/models - skills/skills/ai-research/inference-serving-vllm/references/troubleshooting.md, line 400
curl http://localhost:8000/v1/completions \
Safer alternatives
Low-risk skills in the same category (devops) that look related. Check that one does what you need.
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'serving-llms-vllm' ] || [ -L ~/.agents/skills/'serving-llms-vllm' ]; then echo 'A skill folder named serving-llms-vllm already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/artubss/SKILLS-CLAUDE-CODE' "$d" && git -C "$d" checkout --quiet 'ac67ed85889b15fa9e784e2a93a83f8916870698' -- 'skills/skills/ai-research/inference-serving-vllm' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/skills/ai-research/inference-serving-vllm' ~/.agents/skills/'serving-llms-vllm' && rm -rf "$d"; fi
Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'serving-llms-vllm' ~/.claude/skills/'serving-llms-vllm' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.
Badge for your README
The badge for artubss/SKILLS-CLAUDE-CODE shows the score of its lowest-scoring skill.

[](https://zalavijaysinh.github.io/skilltrust/repos/artubss/SKILLS-CLAUDE-CODE/)
Score history
| Date | Version | Score |
|---|
| 2026-11-08 | ac67ed8 | 100 |