Source: https://seerepo.com/compare/hpcaitech/ColossalAI/vs/OpenBMB/MiniCPM-V
Markdown source: https://seerepo.com/compare/hpcaitech/ColossalAI/vs/OpenBMB/MiniCPM-V.md
Description: ColossalAI and MiniCPM-V share 26 technologies: FastAPI, uvicorn, Gradio, seaborn, matplotlib, Rich, OpenAI, scikit-learn, sentence-transformers, tiktoken, torch, transformers, peft, flash-attn, timm, bitsandbytes, einops, accelerate, sentencepiece, tokenizers, torchaudio, torchvision, pillow, jsonlines, Pydantic, and psutil. Both are written in Python.

# ColossalAI vs MiniCPM-V

ColossalAI and MiniCPM-V share 26 technologies: FastAPI, uvicorn, Gradio, seaborn, matplotlib, Rich, OpenAI, scikit-learn, sentence-transformers, tiktoken, torch, transformers, peft, flash-attn, timm, bitsandbytes, einops, accelerate, sentencepiece, tokenizers, torchaudio, torchvision, pillow, jsonlines, Pydantic, and psutil. Both are written in Python.

- [hpcaitech/ColossalAI](https://seerepo.com/r/hpcaitech/ColossalAI): Making large AI models cheaper, faster and more accessible
- [OpenBMB/MiniCPM-V](https://seerepo.com/r/OpenBMB/MiniCPM-V): See, hear, and interact on your local devices.

## What they share and what sets them apart

- In common: FastAPI, uvicorn, Gradio, seaborn, matplotlib, Rich, OpenAI, scikit-learn, sentence-transformers, tiktoken, torch, transformers, peft, flash-attn, timm, bitsandbytes, einops, accelerate, sentencepiece, tokenizers, torchaudio, torchvision, pillow, jsonlines, Pydantic, psutil
- Only in ColossalAI: chromadb, Hugging Face, anyio, Ray, SQLAlchemy, ModelScope, LangChain, triton, diffusers, datasets, safetensors, vLLM, galore-torch, math-verify, jinja2, markdown-it-py, markupsafe, mdurl, pypdf, unstructured, annotated-types, pydantic-core
- Only in MiniCPM-V: webdataset, AIOHTTP, cycler, fonttools, sphinx-design, contourpy, fairscale, gradio-client, librosa, onnxruntime, pycocotools, sacrebleu, umap-learn, vector-quantize-pytorch, vocos, nltk, opencv-python, deepspeed, pycocoevalcap, spaCy, docutils, markdown2, myst-parser, openpyxl, sphinxcontrib-jquery, xlsxwriter, decord, imageio, moviepy, validators

## Side by side

| | ColossalAI | MiniCPM-V |
|---|---|---|
| Size | 317,403 lines written, 974 code files | 36,999 lines written, 151 code files |
| Who writes it | 0.3% of its commits signed by AI. With Codex and Claude Code | 1.1% of its commits signed by AI. With Cursor and Codex |
| Activity | Last push November 6, 2026, 3,887 commits, 41,430 stars | Last push October 30, 2026, 645 commits, 27,095 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 MiniCPM-V?

ColossalAI, with 317,403 lines written; MiniCPM-V has 36,999.

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

### Which has more GitHub stars, ColossalAI or MiniCPM-V?

ColossalAI, with 41,430 stars; MiniCPM-V has 27,095.

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

### Which has more tests, ColossalAI or MiniCPM-V?

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 MiniCPM-V?

ColossalAI: its last push was on November 6, 2026, and MiniCPM-V's on October 30, 2026.

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

### Which has more commits signed by AI, ColossalAI or MiniCPM-V?

MiniCPM-V: an AI signed 1.1% of its commits, with Cursor and Codex; in ColossalAI, 0.3%.

## Sources

- hpcaitech/ColossalAI: Read on November 6, 2026, at commit da8f5c2 (https://github.com/hpcaitech/ColossalAI/tree/da8f5c2dd56f97d3d23d3d222b114e1a3d4710f5)
- OpenBMB/MiniCPM-V: Read on November 8, 2026, at commit 47e1fa7 (https://github.com/OpenBMB/MiniCPM-V/tree/47e1fa75b45b8c122ca2a52150762bf6183f1c5e)

## 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.