lorax:基于 LoRA 技术的多适配器大模型推理服务项目

Star0

Star0

Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs

Branch84 Tags23

Introduction

面向数千个细调大型语言模型的弹性扩展多LoRA推理服务器【此简介由AI生成】

Apache-2.0 Python 901Commitsfine-tuning gpt llama llm llm-inference llm-serving llmops model-serving pytorch transformers

Customize your domain

333.81 K325Visit GitHub