home/categories/machine-learning/doanchienthangdev-omgkit-plugin-skills-ai-engineering-inference-optimization-skill-md
machine-learningdata-ai

inference-optimization

Optimizing AI inference - quantization, speculative decoding, KV cache, batching, caching strategies. Use when reducing latency, lowering costs, or scaling AI serving.

doanchienthangdev
maintainer
doanchienthangdev
Updated 1/8/2026
Stars
1
Forks
0
quick start

Installation and usage

Optimizing AI inference - quantization, speculative decoding, KV cache, batching, caching strategies. Use when reducing latency, lowering costs, or scaling AI serving.

Installation
$ install --globalskills.sh
Usage

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

skills use inference-optimization