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

llm-aidata-ai

high-performance-inference

Name: high-performance-inference
Author: yonatangross

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

檢視原始碼 llm-ai

maintainer

yonatangross

更新於 1/19/2026

星標

分支

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.

安裝

$ install --globalskills.sh

使用

安裝後，您可以透過在終端機執行以下指令來使用此技能：

skills use high-performance-inference