Source: https://seerepo.com/compare/rohitg00/ai-engineering-from-scratch/vs/vllm-project/vllm
Markdown source: https://seerepo.com/compare/rohitg00/ai-engineering-from-scratch/vs/vllm-project/vllm.md
Description: ai-engineering-from-scratch and vllm share 10 technologies: OpenAI, tokenizers, torchaudio, transformers, torch, torchvision, tiktoken, MCP, datasets, and pillow. Both are written in Python.

# ai-engineering-from-scratch vs vllm

ai-engineering-from-scratch and vllm share 10 technologies: OpenAI, tokenizers, torchaudio, transformers, torch, torchvision, tiktoken, MCP, datasets, and pillow. Both are written in Python.

- [rohitg00/ai-engineering-from-scratch](https://seerepo.com/r/rohitg00/ai-engineering-from-scratch): Learn AI Engineering! Learn it. Build it. Ship it for others.
- [vllm-project/vllm](https://seerepo.com/r/vllm-project/vllm): A high-throughput and memory-efficient inference and serving engine for LLMs

## What they share and what sets them apart

- In common: OpenAI, tokenizers, torchaudio, transformers, torch, torchvision, tiktoken, MCP, datasets, pillow
- Only in ai-engineering-from-scratch: Anthropic, Hono, matplotlib, accelerate, librosa, scikit-learn, google-adk, LangChain, shiki, Zod, @hono/node-server, @mastra/core
- Only in vllm: FastAPI, axum, gitdb, pyzmq, Hugging Face, Tokio, starlette, Ray, AIOHTTP, tower, mkdocs-material, indicatif, NVIDIA, peft, quack-kernels, sentencepiece, einops, safetensors, triton, markdown, markupsafe, pymdown-extensions, image, jinja2, Pydantic, msgspec, jsonschema, pydantic-core, opentelemetry-api, python-json-logger, tracing, prometheus-client, psutil, tracing-subscriber, OpenTelemetry, opentelemetry-sdk, prometheus-fastapi-instrumentator

## Side by side

| | ai-engineering-from-scratch | vllm |
|---|---|---|
| Size | 506,014 lines written, 2,340 code files | 2,375,117 lines written, 3,289 code files |
| Who writes it | 0.8% of its commits signed by AI. With Claude Code and Devin | 12.8% of its commits signed by AI. With Claude Code, Codex, Gemini CLI, Cursor, GitHub Copilot, Devin, Mistral Vibe, CodeRabbit, Factory, and Qwen Code |
| Activity | Last push November 4, 2026, 2,431 commits, 76,859 stars | Last push November 4, 2026, 24,593 commits, 96,302 stars |
| Tests | 781 test files. 17.3% of its code files have a test that imports them | 2,419 test files. 60.2% 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, ai-engineering-from-scratch or vllm?

vllm, with 2,375,117 lines written; ai-engineering-from-scratch has 506,014.

The proof: [vllm-project/vllm's code at commit 75f6761](https://github.com/vllm-project/vllm/tree/75f67614971a44050140e3422c1a65fe5004a72b)

### Which has more GitHub stars, ai-engineering-from-scratch or vllm?

vllm, with 96,302 stars; ai-engineering-from-scratch has 76,859.

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

### Which has more tests, ai-engineering-from-scratch or vllm?

vllm, with 2,419 test files; ai-engineering-from-scratch has 781.

The proof: [vllm-project/vllm's code at commit 75f6761](https://github.com/vllm-project/vllm/tree/75f67614971a44050140e3422c1a65fe5004a72b)

### Which was updated more recently, ai-engineering-from-scratch or vllm?

Both got their last push on November 4, 2026.

The proof: [vllm-project/vllm's commits on GitHub](https://github.com/vllm-project/vllm/commits)

### Which has more commits signed by AI, ai-engineering-from-scratch or vllm?

vllm: an AI signed 12.8% of its commits, with Claude Code, Codex, Gemini CLI, Cursor, GitHub Copilot, Devin, Mistral Vibe, CodeRabbit, Factory, and Qwen Code; in ai-engineering-from-scratch, 0.8%.

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

## Sources

- rohitg00/ai-engineering-from-scratch: Read on November 4, 2026, at commit 8fec9cc (https://github.com/rohitg00/ai-engineering-from-scratch/tree/8fec9cc19ee7c73b92582899b5455333d30d718e)
- vllm-project/vllm: Read on November 4, 2026, at commit 75f6761 (https://github.com/vllm-project/vllm/tree/75f67614971a44050140e3422c1a65fe5004a72b)

## 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.