Source: https://seerepo.com/compare/state-spaces/mamba/vs/vllm-project/vllm
Markdown source: https://seerepo.com/compare/state-spaces/mamba/vs/vllm-project/vllm.md
Description: mamba and vllm share 5 technologies: quack-kernels, torch, triton, einops, and transformers. Both are written in Python.

# mamba vs vllm

mamba and vllm share 5 technologies: quack-kernels, torch, triton, einops, and transformers. Both are written in Python.

- [state-spaces/mamba](https://seerepo.com/r/state-spaces/mamba): Mamba SSM architecture
- [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: quack-kernels, torch, triton, einops, transformers
- Only in mamba: apache-tvm-ffi
- Only in vllm: FastAPI, axum, gitdb, pyzmq, Hugging Face, Tokio, starlette, Ray, AIOHTTP, tower, mkdocs-material, indicatif, NVIDIA, OpenAI, peft, sentencepiece, safetensors, torchvision, datasets, torchaudio, MCP, tokenizers, tiktoken, markdown, markupsafe, pymdown-extensions, pillow, 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

| | mamba | vllm |
|---|---|---|
| Size | 28,235 lines written, 43 code files | 2,375,117 lines written, 3,289 code files |
| Who writes it | 0.5% of its commits signed by AI. With GitHub Copilot | 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 July 22, 2026, 219 commits, 18,976 stars | Last push November 4, 2026, 24,593 commits, 96,302 stars |
| Tests | 11 test files. 51.2% 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, mamba or vllm?

vllm, with 2,375,117 lines written; mamba has 28,235.

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

### Which has more GitHub stars, mamba or vllm?

vllm, with 96,302 stars; mamba has 18,976.

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

### Which has more tests, mamba or vllm?

vllm, with 2,419 test files; mamba has 11.

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

### Which was updated more recently, mamba or vllm?

vllm: its last push was on November 4, 2026, and mamba's on July 22, 2026.

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

### Which has more commits signed by AI, mamba 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 mamba, 0.5%.

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

## Sources

- state-spaces/mamba: Read on November 6, 2026, at commit e9594ce (https://github.com/state-spaces/mamba/tree/e9594ce1c732d97440f0332fdc43170a2294dbfa)
- 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.