home/categories/llm-ai/yonatangross-skillforge-claude-plugin-skills-high-performance-inference-skill-md
llm-aidata-ai

high-performance-inference

High-performance LLM inference with vLLM, quantization (AWQ, GPTQ, FP8), speculative decoding, and edge deployment. Use when optimizing inference latency, throughput, or memory.

yonatangross
maintainer
yonatangross
Updated 1/19/2026
Stars
26
Forks
4
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.

Installation
$ install --globalskills.sh
Usage

Once installed, you can use this skill by running the following command in your terminal:

skills use high-performance-inference