Back to skills directory

LLM Inference Serving

大模型推理服务技能,对比 vLLM、TGI、TensorRT-LLM 等推理引擎的吞吐、延迟与部署方案。

LLM Inference Serving is an Agent skill for Data & Visualization. 大模型推理服务技能,对比 vLLM、TGI、TensorRT-LLM 等推理引擎的吞吐、延迟与部署方案。 Tags: LLM · 推理 · inference · vLLM · TGI · TensorRT-LLM.

Data & Visualization16.0k installsAuthor: obraVisit

What is LLM Inference Serving

LLM Inference Serving packages a Data & Visualization workflow for agents. 大模型推理服务技能,对比 vLLM、TGI、TensorRT-LLM 等推理引擎的吞吐、延迟与部署方案。

Install LLM Inference Serving in Cursor / Claude / Codex

Claude Code Install with the command on this page, or place the skill in ~/.claude/skills or project .claude/skills so Claude can detect LLM Inference Serving.

Cursor After the install command writes the skill directory, invoke LLM Inference Serving by name in the Cursor agent.

Codex Install into the Codex skills directory and call it by name. If only a generic command is listed, run it locally and confirm Codex can see the skill.

One-click Install

Run the following command in your terminal to install the skill into your AI agent:

npx skillsadd obra/superpowers

How to Use

Claude Code: Place the skill in ~/.claude/skills (personal) or the project .claude/skills directory, and Claude will auto-detect it.

Cursor / Windsurf: After installing via npx skillsadd, the skill directory is placed in the configured path.

Codex CLI: After installation it loads automatically from the skills directory and is invoked by name.

Tags

LLM推理inferencevLLMTGITensorRT-LLM部署serving

Similar recommendations

FAQ

What is LLM Inference Serving for?

LLM Inference Serving is a Data & Visualization skill. 大模型推理服务技能,对比 vLLM、TGI、TensorRT-LLM 等推理引擎的吞吐、延迟与部署方案。

Can Claude, Cursor, and Codex all use LLM Inference Serving?

Yes if the client supports Agent Skills and has loaded the skill directory. Check the project home for compatibility notes.

What similar skills exist?

Related items come from the same Data & Visualization group so you can pick a closer workflow.