home/categories/llm-ai/yonatangross-skillforge-claude-plugin-skills-high-performance-inference-skill-md
quick start
Installation and usage
High-performance LLM inference with vLLM, quantization (AWQ, GPTQ, FP8), speculative decoding, and edge deployment. Use when optimizing inference latency, throughput, or memory.
安装
$ install --globalskills.sh
使用
安装后，您可以通过在终端运行以下命令来使用此技能：
skills use high-performance-inference