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.

davila7
maintainer
davila7
Mis à jour 1/20/2026
Étoiles
17577
Forks
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.

Installation
$ install --globalskills.sh
Utilisation

Après l'installation, vous pouvez utiliser ce skill en exécutant la commande suivante dans votre terminal :

skills use serving-llms-vllm