home/categories/llm-ai/davila7-claude-code-templates-cli-tool-components-skills-ai-research-inference-serving-vllm-skill-md
llm-aidata-ai
serving-llms-vllm
Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.
maintainer
davila7
์
๋ฐ์ดํธ๋จ 2026. 1. 20.
์คํ
17577
ํฌํฌ
1576
quick start
Installation and usage
Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.
์ค์น
$ install --globalskills.sh
์ฌ์ฉ๋ฒ
์ค์น ํ ํฐ๋ฏธ๋์์ ๋ค์ ๋ช ๋ น์ ์คํํ์ฌ ์ด ์คํฌ์ ์ฌ์ฉํ ์ ์์ต๋๋ค:
skills use serving-llms-vllm