unsloth-inference

Name: unsloth-inference
Author: cuba6112

Deploying fine-tuned models for production inference using native kernel optimization, vLLM, or SGLang. Triggers: inference, serving, vllm, sglang, for_inference, model merging, openai api.

檢視原始碼 llm-ai

maintainer

cuba6112

更新於 12/26/2025

星標

分支

quick start

Installation and usage

Deploying fine-tuned models for production inference using native kernel optimization, vLLM, or SGLang. Triggers: inference, serving, vllm, sglang, for_inference, model merging, openai api.

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 unsloth-inference