Source: https://seerepo.com/compare/hpcaitech/ColossalAI/vs/InternLM/lmdeploy
Markdown source: https://seerepo.com/compare/hpcaitech/ColossalAI/vs/InternLM/lmdeploy.md
Description: ColossalAI and lmdeploy share 18 technologies: FastAPI, uvicorn, Ray, matplotlib, OpenAI, tiktoken, torch, transformers, triton, peft, datasets, safetensors, einops, accelerate, sentencepiece, torchvision, pillow, and Pydantic. Both are written in Python.

# ColossalAI vs lmdeploy

ColossalAI and lmdeploy share 18 technologies: FastAPI, uvicorn, Ray, matplotlib, OpenAI, tiktoken, torch, transformers, triton, peft, datasets, safetensors, einops, accelerate, sentencepiece, torchvision, pillow, and Pydantic. Both are written in Python.

- [hpcaitech/ColossalAI](https://seerepo.com/r/hpcaitech/ColossalAI): Making large AI models cheaper, faster and more accessible
- [InternLM/lmdeploy](https://seerepo.com/r/InternLM/lmdeploy): LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

## What they share and what sets them apart

- In common: FastAPI, uvicorn, Ray, matplotlib, OpenAI, tiktoken, torch, transformers, triton, peft, datasets, safetensors, einops, accelerate, sentencepiece, torchvision, pillow, Pydantic
- Only in ColossalAI: chromadb, Hugging Face, anyio, Gradio, seaborn, Rich, SQLAlchemy, ModelScope, rouge, scikit-learn, sentence-transformers, colossalai, LangChain, diffusers, flash-attn, bitsandbytes, vLLM, galore-torch, loralib, math-verify, torchaudio, jinja2, markdown-it-py, markupsafe, mdurl, pypdf, unstructured, jsonlines, annotated-types, gpustat, psutil, fabric
- Only in lmdeploy: pyzmq, Anthropic, AIOHTTP, sphinx-book-theme, apache-tvm-ffi, flash-linear-attention, openai-harmony, partial-json-parser, qwen-vl-utils, rdkit, transformers-stream-generator, xgrammar, torch-npu, timm, markdown, myst-parser, prometheus-client

## Side by side

| | ColossalAI | lmdeploy |
|---|---|---|
| Size | 328,017 lines written, 993 code files | 299,565 lines written, 789 code files |
| Who writes it | 0.3% of its commits signed by AI. With Codex and Claude Code | 1.2% of its commits signed by AI. With Claude Code, GitHub Copilot, Cursor, and OpenHands |
| Activity | Last push November 18, 2026, 3,929 commits, 41,420 stars | Last push November 17, 2026, 2,189 commits, 8,149 stars |
| Tests | 561 test files. 1.1% of its code files have a test that imports them | 336 test files. 44.1% 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 lmdeploy?

ColossalAI, with 328,017 lines written; lmdeploy has 299,565.

The proof: [hpcaitech/ColossalAI's code at commit 14d1c15](https://github.com/hpcaitech/ColossalAI/tree/14d1c15147564603d4564198f38af1ea3c42be92)

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

ColossalAI, with 41,420 stars; lmdeploy has 8,149.

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

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

ColossalAI, with 561 test files; lmdeploy has 336.

The proof: [hpcaitech/ColossalAI's code at commit 14d1c15](https://github.com/hpcaitech/ColossalAI/tree/14d1c15147564603d4564198f38af1ea3c42be92)

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

ColossalAI: its last push was on November 18, 2026, and lmdeploy's on November 17, 2026.

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

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

lmdeploy: an AI signed 1.2% of its commits, with Claude Code, GitHub Copilot, Cursor, and OpenHands; in ColossalAI, 0.3%.

The proof: [the commits each tool signed in InternLM/lmdeploy](https://seerepo.com/r/InternLM/lmdeploy/ai)

## Sources

- hpcaitech/ColossalAI: Read on November 18, 2026, at commit 14d1c15 (https://github.com/hpcaitech/ColossalAI/tree/14d1c15147564603d4564198f38af1ea3c42be92)
- InternLM/lmdeploy: Read on November 17, 2026, at commit fc33f69 (https://github.com/InternLM/lmdeploy/tree/fc33f69736ff48c10ad720593b021dcdaedcb80d)

## 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.
