# Kun-Tai Wu

> Kun-Tai Wu is maintainer. Decision 3.0 on Anchor Terminal, with grades, an about and public profiles.

- Canonical: https://www.anchorterminal.com/people/kun-tai-wu/
- Markdown: https://www.anchorterminal.com/people/kun-tai-wu/index.md (~700 tokens)
- Slim: https://www.anchorterminal.com/people/kun-tai-wu/index.min.md (~480 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/people/kun-tai-wu/index.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- MCP: https://www.anchorterminal.com/mcp (the whole catalogue as tools, no key)
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)
- Updated: 2026-10-28

Maintainer.

- LinkedIn: https://www.linkedin.com/in/kun-tai-wu/
- GitHub: https://github.com/WUKUNTAI-0211

## What Kun-Tai builds

- [Decision 3.0](https://www.anchorterminal.com/tools/decision-3.md), graded B, 63.6/100, in Decision models. Decision 3.0 is a family of open-weight multimodal decision models from the vLLM Semantic Router team, 0.6B to 27B, under Apache-2.0. They answer choice, yes-or-no and score questions about text, images and video with a probability per option. Maintainer, researched 2026-10-28.

## Works with

- [Aayush Saini](https://www.anchorterminal.com/people/aayush-saini/), Maintainer
- [Huamin Chen](https://www.anchorterminal.com/people/huamin-chen/), Maintainer and steering committee member (industry track); proposed the project in early 2025
- [Xunzhuo Liu](https://www.anchorterminal.com/people/xunzhuo-liu/), Co-founder, maintainer and steering committee member (industry track)

## Questions

### Who is Kun-Tai Wu?

Kun-Tai Wu is maintainer.

### What does vLLM Semantic Router Team make?

Anchor Terminal lists Decision 3.0 from vLLM Semantic Router Team. Decision 3.0 is a family of open-weight multimodal decision models from the vLLM Semantic Router team, 0.6B to 27B, under Apache-2.0. They answer choice, yes-or-no and score questions about text, images and video with a probability per option.

### How are Kun-Tai's tools graded?

Decision 3.0 is graded B, 63.6 out of 100, on Anchor Terminal's benchmark, which scores every listing against the same checklist.

## Sources

- https://vllm-sr.ai/

These are the people building the tools we list, named for their public role in the company or project behind a listing, from public pages, with the date it was researched. They don't work for Anchor Terminal (our own team is on the about page, /about/#author). We show public roles, public profiles and what the listing pages show, nothing private. To correct something, send an about or a photo, or have a page removed, write to privacy@anchorterminal.com.

---

Query this catalogue directly over MCP: https://www.anchorterminal.com/mcp (Streamable HTTP, no key). How: https://www.anchorterminal.com/agents/#mcp