Source: https://seerepo.com/compare/hpcaitech/ColossalAI/vs/OpenBMB/VoxCPM
Markdown source: https://seerepo.com/compare/hpcaitech/ColossalAI/vs/OpenBMB/VoxCPM.md
Description: ColossalAI and VoxCPM share 11 technologies: Hugging Face, Gradio, matplotlib, ModelScope, torch, transformers, datasets, safetensors, einops, torchaudio, and Pydantic. Both are written in Python.

# ColossalAI vs VoxCPM

ColossalAI and VoxCPM share 11 technologies: Hugging Face, Gradio, matplotlib, ModelScope, torch, transformers, datasets, safetensors, einops, torchaudio, and Pydantic. Both are written in Python.

- [hpcaitech/ColossalAI](https://seerepo.com/r/hpcaitech/ColossalAI): Making large AI models cheaper, faster and more accessible
- [OpenBMB/VoxCPM](https://seerepo.com/r/OpenBMB/VoxCPM): VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning

## What they share and what sets them apart

- In common: Hugging Face, Gradio, matplotlib, ModelScope, torch, transformers, datasets, safetensors, einops, torchaudio, Pydantic
- Only in ColossalAI: FastAPI, uvicorn, chromadb, anyio, Ray, seaborn, Rich, SQLAlchemy, OpenAI, scikit-learn, sentence-transformers, tiktoken, LangChain, triton, peft, diffusers, flash-attn, timm, bitsandbytes, vLLM, accelerate, galore-torch, math-verify, sentencepiece, tokenizers, torchvision, jinja2, markdown-it-py, markupsafe, mdurl, pypdf, unstructured, pillow, jsonlines, annotated-types, pydantic-core, psutil
- Only in VoxCPM: funasr, librosa, wetext, torchcodec, spaces

## Side by side

| | ColossalAI | VoxCPM |
|---|---|---|
| Size | 317,403 lines written, 974 code files | 12,877 lines written, 41 code files |
| Who writes it | 0.3% of its commits signed by AI. With Codex and Claude Code | 10.1% of its commits signed by AI. With Cursor and Claude Code |
| Activity | Last push November 6, 2026, 3,887 commits, 41,430 stars | Last push November 5, 2026, 149 commits, 41,114 stars |
| Tests | 505 test files. 1.1% of its code files have a test that imports them | 10 test files. 43.9% of its code files have a test that imports them |

- 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 VoxCPM?

ColossalAI, with 317,403 lines written; VoxCPM has 12,877.

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

### Which has more GitHub stars, ColossalAI or VoxCPM?

ColossalAI, with 41,430 stars; VoxCPM has 41,114.

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

### Which has more tests, ColossalAI or VoxCPM?

ColossalAI, with 505 test files; VoxCPM has 10.

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

### Which was updated more recently, ColossalAI or VoxCPM?

ColossalAI: its last push was on November 6, 2026, and VoxCPM's on November 5, 2026.

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

### Which has more commits signed by AI, ColossalAI or VoxCPM?

VoxCPM: an AI signed 10.1% of its commits, with Cursor and Claude Code; in ColossalAI, 0.3%.

## Sources

- hpcaitech/ColossalAI: Read on November 6, 2026, at commit da8f5c2 (https://github.com/hpcaitech/ColossalAI/tree/da8f5c2dd56f97d3d23d3d222b114e1a3d4710f5)
- OpenBMB/VoxCPM: Read on November 6, 2026, at commit 4b8dd44 (https://github.com/OpenBMB/VoxCPM/tree/4b8dd4440d33396b3f429201f8af0529b4d2c601)

## 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.