GV

GeezerVison

The World Wide Web, restored to 800 pixels of glory.

Home|About|Gaming cabinet|Archives|How it works|Starter sites

On this site

  • Sign in
  • ActionsCI/CD and automation
  • CodespacesCloud development environments
  • All Features
  • Documentation
  • Training
  • Certifications
  • Build with Copilot
  • Customize Copilot
  • Integrations
  • Trending repos
  • GitHub Sponsors
  • Developer articles
  • Enterprises

This view

  • Original page
  • New address

GeezerVison is showing github.com — Anionex - Overview

@Anionex Anionex Follow
More
  • Overview
  • Repositories
  • Projects
  • Packages
  • Stars
@Anionex
Anionex
Follow
View Anionex's full-sized avatar

anionex Anionex

Follow
order and romance, I suppose.
384 followers · 18 following
  • Earth
  • anionex.me
  • @anion_ex

Achievements

Achievement: YOLOAchievement: Pull Sharkx3Achievement: Pair Extraordinairex2Achievement: Starstruckx4Achievement: Quickdraw

Achievements

Achievement: YOLOAchievement: Pull Sharkx3Achievement: Pair Extraordinairex2Achievement: Starstruckx4Achievement: Quickdraw

Organizations

@omdsh-dev
More
  • Overview
  • Repositories
  • Projects
  • Packages
  • Stars
Anionex/README.md

evening

Hi 👋, I'm anionex

X (Twitter) Bilibili

Global Star Rank

Anionex | Trendshift


  • 🌐 中文 · English
  • 🏄‍♂️ A Gen Z tinkerer
  • 🔗 Website: anionex.me
  • 📚 Interests: LLMs, AIGC, deploying models, trying new things
  • 📫 Reach me at: [email protected]

🛠️ projects

I built an AI-native slides generator 🍌 banana-slides (15k+⭐) 🌐: bananaslides.online

also built:

  • agent-vision-toolkit(1.2k+⭐) — A vision toolkit for text-only agents handling multi-step visual tasks
  • dsh-vision-toolkit(900+⭐) — the first(day0) comprehensive native visual plugin for deepseek harness.
  • treeAI — chat with LLMs in the form of a tree
  • cherry-studio-with-js-plugins — a plugin system for Cherry Studio

Some projects I've contributed to:

  • vllm-project/vllm (96.8k⭐) — Hunyuan dense model inference regression fix.
  • vercel-labs/agent-browser (50.1k⭐) — Snapshot schema fix to restore cursor-interactive element detection.
  • JustVugg/colibri (50k⭐) — Single-frame CPU VAE encoding for Qwen-Image.
  • vllm-project/vllm-ascend (3.1k⭐) — New-format W4A8 dynamic quantization support for linear layers.
  • ddalcu/mlx-serve (2.4k⭐) — Prefix KV caching for faster multi-reference Qwen-Image editing.
  • OSU-NLP-Group/TravelPlanner (569⭐) — Planner tool initialization fix to prevent duplicate instances.



Pinned Loading

  1. banana-slides banana-slides Public

    一站式原生AI PPT生成应用,几分钟内生成一套幻灯片; 支持上传任意模板图片,上传任意素材&智能解析,一句话/大纲/页面描述自动生成PPT,口头修改指定区域、一键导出可编辑ppt、视频等 - An AI-native slides generator based on nano banana/gpt-image🏞️

    Python 16k 1.8k

  2. agent-vision-toolkit agent-vision-toolkit Public

    为纯文本模型"看图“设计更好的视觉工具箱和技能,支持多图理解,图片问答,前端UI还原、GUI 自动化等,并可选无缝接入多个主流agent,直接识别粘贴图片| A vision toolkit and skill designed for text-only llms — image Q&A, long-screenshot OCR, frontend UI restoration, and …

    Python 1.3k 50

  3. dsh-vision-toolkit dsh-vision-toolkit Public

    [dsh]为纯文本模型设计更强大的视觉工具箱:一行安装使用、粘贴图片直接识别、多张图片问答、截图到前端UI 还原等|DeepSeek Harness-native integration for agent-vision-toolkit: image Q&A, long-screenshot OCR, UI restoration, grounding, pixel diff, Artifa…

    TypeScript 942 48

  4. vllm-project/vllm vllm-project/vllm Public

    A high-throughput and memory-efficient inference and serving engine for LLMs

    Python 96.8k 24.7k

Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.

Uh oh!

There was an error while loading. Please reload this page.

You are visitor 01402503 — GeezerVison does not store the pages you look up.
Best viewed with Netscape Navigator 4.7 or Internet Explorer 6 at 800×600. No cookies required.