npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

rocm-deploy

v0.5.0

Published

CLI tool for deploying, fine-tuning, and serving LLMs on AMD ROCm via ModelScope

Readme

rocm-deploy

在 AMD ROCm 上通过 ModelScope 部署、微调和提供 LLM 服务的命令行工具。

安装

npm install -g rocm-deploy

本地构建:

cd src/npm/rocm-deploy
npm link

环境要求

  • Node.js 18+
  • Python 3.8+
  • modelscope Python 包(pip install modelscope
  • ROCm 驱动(可选,用于 GPU 加速)

CLI 使用

# 启动 API 服务器(端口 8080)
rocm-deploy serve -p 8080

# 启动 TUI 界面
rocm-deploy

# 从 ModelScope 下载模型
rocm-deploy download google/gemma-4-E4B-it

# 下载数据集(默认使用 Moemuu/Muice-Dataset)
rocm-deploy download-dataset

# 从 ModelScope ID 下载数据集
rocm-deploy download-dataset -d my-org/my-dataset

# 从 URL 下载数据集
rocm-deploy download-dataset -u https://example.com/data.zip

# 从本地路径导入数据集
rocm-deploy download-dataset -l /path/to/data

# 微调模型
rocm-deploy finetune --model google/gemma-4-E4B-it --dataset Moemuu/Muice-Dataset

# 管理 API 密钥
rocm-deploy create-key -n "my-app"
rocm-deploy list-keys
rocm-deploy revoke-key <key>

# 列出已下载的模型/数据集
rocm-deploy list-models
rocm-deploy list-datasets

API 服务器

启动:rocm-deploy serve -p <port>。设置 ROCM_DEPLOY_ADMIN_KEY 环境变量以启用管理员认证。

接口列表

| 方法 | 路径 | 认证 | 说明 | |--------|------|------|------| | GET | / | 无 | 服务信息 | | GET | /health | 无 | 健康检查 | | GET | /v1/models | 任意 | 列出可用模型 | | POST | /v1/chat/completions | 任意 | OpenAI 兼容对话接口 | | GET | /v1/admin/models | 管理员 | 列出已下载模型 | | POST | /v1/admin/models/download | 管理员 | 下载模型 | | GET | /v1/admin/datasets | 管理员 | 列出已下载数据集 | | POST | /v1/admin/datasets/download | 管理员 | 下载数据集(支持 ModelScope/URL/本地路径) | | GET | /v1/admin/finetune | 管理员 | 列出微调任务 | | POST | /v1/admin/finetune | 管理员 | 启动微调 | | POST | /v1/admin/save-model | 管理员 | 保存微调后的模型副本 | | GET | /v1/admin/keys | 管理员 | 列出 API 密钥 | | POST | /v1/admin/keys | 管理员 | 创建 API 密钥 | | DELETE | /v1/admin/keys | 管理员 | 撤销 API 密钥 |

环境变量

  • ROCM_DEPLOY_ADMIN_KEY — 管理员 API 密钥(不设置时自动生成)

环境初始化

# 自动安装 Python 依赖(modelscope 等)
rocm-deploy setup

许可证

MIT