Source: https://seerepo.com/compare/hpcaitech/ColossalAI/vs/Wan-Video/Wan2.2
Markdown source: https://seerepo.com/compare/hpcaitech/ColossalAI/vs/Wan-Video/Wan2.2.md
Description: ColossalAI and Wan2.2 share 13 technologies: matplotlib, Rich, ModelScope, torch, transformers, peft, diffusers, flash-attn, accelerate, sentencepiece, tokenizers, torchaudio, and torchvision. Both are written in Python.

# ColossalAI vs Wan2.2

ColossalAI and Wan2.2 share 13 technologies: matplotlib, Rich, ModelScope, torch, transformers, peft, diffusers, flash-attn, accelerate, sentencepiece, tokenizers, torchaudio, and torchvision. Both are written in Python.

- [hpcaitech/ColossalAI](https://seerepo.com/r/hpcaitech/ColossalAI): Making large AI models cheaper, faster and more accessible
- [Wan-Video/Wan2.2](https://seerepo.com/r/Wan-Video/Wan2.2): Wan: Open and Advanced Large-Scale Video Generative Models

## What they share and what sets them apart

- In common: matplotlib, Rich, ModelScope, torch, transformers, peft, diffusers, flash-attn, accelerate, sentencepiece, tokenizers, torchaudio, torchvision
- Only in ColossalAI: FastAPI, uvicorn, chromadb, Hugging Face, anyio, Ray, Gradio, seaborn, SQLAlchemy, OpenAI, scikit-learn, sentence-transformers, tiktoken, LangChain, triton, datasets, timm, safetensors, bitsandbytes, vLLM, einops, galore-torch, math-verify, jinja2, markdown-it-py, markupsafe, mdurl, pypdf, unstructured, pillow, jsonlines, annotated-types, pydantic-core, Pydantic, psutil
- Only in Wan2.2: pyarrow, Lightning, conformer, openai-whisper, pyworld, wetext, opencv-python, dashscope, librosa, onnxruntime, imageio-ffmpeg, decord, imageio, loguru

## Side by side

| | ColossalAI | Wan2.2 |
|---|---|---|
| Size | 317,403 lines written, 974 code files | 19,152 lines written, 57 code files |
| Who writes it | 0.3% of its commits signed by AI. With Codex and Claude Code | 0% of its commits signed by AI |
| Activity | Last push November 6, 2026, 3,887 commits, 41,430 stars | Last push September 21, 2026, 40 commits, 18,418 stars |
| Tests | 505 test files. 1.1% of its code files have a test that imports them | 0 test files |

- Size: Lines written by people and agents, without generated ones; code files, without tests.
- Who writes it: A commit counts as AI's when it carries its signature: a Co-Authored-By line, its author name or the merge of its branch.
- Activity: From GitHub and its history, on the day SeeRepo read it.
- Tests: The files that test the code, and the share of code files a test imports.

## Frequently asked questions

### Which is bigger, ColossalAI or Wan2.2?

ColossalAI, with 317,403 lines written; Wan2.2 has 19,152.

The proof: [hpcaitech/ColossalAI's code at commit da8f5c2](https://github.com/hpcaitech/ColossalAI/tree/da8f5c2dd56f97d3d23d3d222b114e1a3d4710f5)

### Which has more GitHub stars, ColossalAI or Wan2.2?

ColossalAI, with 41,430 stars; Wan2.2 has 18,418.

The proof: [hpcaitech/ColossalAI on GitHub](https://github.com/hpcaitech/ColossalAI)

### Which has more tests, ColossalAI or Wan2.2?

ColossalAI, with 505 test files.

The proof: [hpcaitech/ColossalAI's code at commit da8f5c2](https://github.com/hpcaitech/ColossalAI/tree/da8f5c2dd56f97d3d23d3d222b114e1a3d4710f5)

### Which was updated more recently, ColossalAI or Wan2.2?

ColossalAI: its last push was on November 6, 2026, and Wan2.2's on September 21, 2026.

The proof: [hpcaitech/ColossalAI's commits on GitHub](https://github.com/hpcaitech/ColossalAI/commits)

### Which has more commits signed by AI, ColossalAI or Wan2.2?

ColossalAI: an AI signed 0.3% of its commits, with Codex and Claude Code.

## Sources

- hpcaitech/ColossalAI: Read on November 6, 2026, at commit da8f5c2 (https://github.com/hpcaitech/ColossalAI/tree/da8f5c2dd56f97d3d23d3d222b114e1a3d4710f5)
- Wan-Video/Wan2.2: Read on November 6, 2026, at commit 1ea34ff (https://github.com/Wan-Video/Wan2.2/tree/1ea34ff48f87168174e12956e200b1d908b1c5ff)

## 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.
