Source: https://seerepo.com/uses/qwen-vl-utils
Markdown source: https://seerepo.com/uses/qwen-vl-utils.md
Description: 10 public repos that SeeRepo read use qwen-vl-utils. It's used most with accelerate, FastAPI, and Ray.

# Open source repos that use qwen-vl-utils

10 public repos that SeeRepo read use qwen-vl-utils. It's used most with accelerate, FastAPI, and Ray.

## Used most with

- accelerate: 3 repos
- FastAPI: 3 repos
- Ray: 3 repos
- transformers: 3 repos
- pyarrow: 2 repos
- torch: 2 repos
- OpenAI: 2 repos
- datasets: 2 repos

## The repos, by stars

1. [verl-project/verl](https://seerepo.com/r/verl-project/verl): Python · 24,243 stars · 9.3% signed by AI — verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework 
2. [voxel51/fiftyone](https://seerepo.com/r/voxel51/fiftyone): TypeScript · 11,299 stars · 1.3% signed by AI — Refine high-quality datasets and visual AI models
3. [StarTrail-org/PixelRAG](https://seerepo.com/r/StarTrail-org/PixelRAG): Python · 10,914 stars · 24.1% signed by AI — https://arxiv.org/abs/2606.28344. The end of web parsing. The beginning of scalable pixel-native search. link: https://pixelrag.ai/
4. [NVlabs/Sana](https://seerepo.com/r/NVlabs/Sana): Python · 9,825 stars · 2.2% signed by AI — SANA & Sol: Efficient Generative Models and Full-Stack Training & Inference Engines for Image, Video, and World Modeling
5. [xorbitsai/inference](https://seerepo.com/r/xorbitsai/inference): Python · 9,655 stars · 0.3% signed by AI — Open-source inference platform for language, vision, embedding, reranking, image, audio, and video models. Deploy with multiple engines across heterogeneous hardware, from a laptop to a distributed cluster. Serve models through OpenAI-compatible APIs.
6. [X-PLUG/MobileAgent](https://seerepo.com/r/X-PLUG/MobileAgent): HTML · 9,379 stars —  Mobile-Agent: The Powerful GUI Agent Family
7. [modelscope/modelscope](https://seerepo.com/r/modelscope/modelscope): Python · 9,218 stars · 0.1% signed by AI — ModelScope: bring the notion of Model-as-a-Service to life.
8. [THUDM/slime](https://seerepo.com/r/THUDM/slime): Python · 8,828 stars · 3.2% signed by AI — slime is an LLM training framework for RL Scaling.
9. [InternLM/lmdeploy](https://seerepo.com/r/InternLM/lmdeploy): Python · 8,149 stars · 1.2% signed by AI — LMDeploy is a toolkit for compressing, deploying, and serving LLMs.
10. [bojieli/ai-infra-book](https://seerepo.com/r/bojieli/ai-infra-book): Python · 8,032 stars · 16.6% signed by AI — 《深入理解 AI Infra：量化分析与系统设计》（李博杰 著）开源书稿：从硬件约束和模型架构出发，量化推导 LLM 推理与训练系统设计。含全书正文、PDF、配套计算工具与实验

## Frequently asked questions

### What is the most popular open source repo that uses qwen-vl-utils?

verl-project/verl, with 24,243 stars on GitHub.

The proof: [verl-project/verl on GitHub](https://github.com/verl-project/verl)

### What other technologies is qwen-vl-utils used with?

With accelerate (3), FastAPI (3), Ray (3), transformers (3), and pyarrow (2), out of the 10 repos that use it.

### What languages are the repos that use qwen-vl-utils written in?

Python (8), HTML (1), and TypeScript (1).

### How many repos that use qwen-vl-utils have commits signed by AI?

9 of the 10; the most, StarTrail-org/PixelRAG, with 24.1% of its commits.

The proof: [the commits each tool signed in StarTrail-org/PixelRAG](https://seerepo.com/r/StarTrail-org/PixelRAG/ai)

## What is your repo built with?

Any public repo, with no account: https://seerepo.com/r/owner/repo/built, with the owner and name it has on GitHub.
