home/categories/machine-learning/melodic-software-claude-code-plugins-plugins-systems-design-skills-llm-serving-patterns-skill-md
machine-learningdata-ai
llm-serving-patterns
LLM inference infrastructure, serving frameworks (vLLM, TGI, TensorRT-LLM), quantization techniques, batching strategies, and streaming response patterns. Use when designing LLM serving infrastructure, optimizing inference latency, or scaling LLM deployments.
maintainer
melodic-software
更新日 1/19/2026
スター
11
フォーク
1
quick start
Installation and usage
LLM inference infrastructure, serving frameworks (vLLM, TGI, TensorRT-LLM), quantization techniques, batching strategies, and streaming response patterns. Use when designing LLM serving infrastructure, optimizing inference latency, or scaling LLM deployments.
インストール
$ install --globalskills.sh
使い方
インストール後、ターミナルで以下のコマンドを実行してこのスキルを使用できます：
skills use llm-serving-patterns