Source: https://seerepo.com/compare/pollen-robotics/microduck/vs/vllm-project/vllm
Markdown source: https://seerepo.com/compare/pollen-robotics/microduck/vs/vllm-project/vllm.md
Description: microduck and vllm share 8 technologies: axum, FastAPI, Tokio, image, jinja2, tracing, tracing-subscriber, and Hugging Face. microduck is written in Rust and vllm in Python.

# microduck vs vllm

microduck and vllm share 8 technologies: axum, FastAPI, Tokio, image, jinja2, tracing, tracing-subscriber, and Hugging Face. microduck is written in Rust and vllm in Python.

- [pollen-robotics/microduck](https://seerepo.com/r/pollen-robotics/microduck): A Tiny biped duck robot 🦆
- [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: axum, FastAPI, Tokio, image, jinja2, tracing, tracing-subscriber, Hugging Face
- Only in microduck: uvicorn, glib, Ratatui, Gradio, ort, av, hound, qrcode, roxmltree
- Only in vllm: gitdb, pyzmq, starlette, Ray, AIOHTTP, tower, mkdocs-material, indicatif, AMD, apache-tvm-ffi, auto-round-lib, conch-triton-kernels, cuda-bindings, cuda-python, cupy-cuda12x, cupy-cuda13x, flashinfer-python, humming-kernels, lm-format-enforcer, mooncake-transfer-engine, mooncake-transfer-engine-rocm, NVIDIA, nvidia-cudnn-frontend, OpenAI, openai-harmony, oss-harmony, peft, quack-kernels, sentencepiece, vllm-bench, vllm-chat, vllm-engine-core-client, vllm-llm, vllm-managed-engine, vllm-parser, vllm-proto, vllm-server, vllm-text, vllm-tokenizer, torch, transformers, xgrammar-structural-tag, einops, llm-multimodal, compressed-tensors, safetensors, triton, mistral-common, xgrammar, partial-json-parser, torchvision, datasets, lmcache, torchaudio, timm, vllm-xpu-kernels, runai-model-streamer, tokenizers, tokenspeed-mla, llguidance, MCP, outlines-core, tpu-inference, fastokens, fastsafetensors, hf-hub, instanttensor, nixl, riptoken, tekken, tensorizer, tiktoken, tiktoken-rs, markdown, markupsafe, mkdocs-material-extensions, parquet, properdocs, pymdown-extensions, selectolax, xlsxwriter, pillow, minijinja, torchcodec, minijinja-contrib, annotated-types, Pydantic, msgspec, validator, jsonschema, pydantic-core, opentelemetry-api, opentelemetry-semantic-conventions-ai, python-json-logger, vllm-metrics, vllm-tracing, prometheus-client, psutil, tracing-futures, model-hosting-container-standards, OpenTelemetry, opentelemetry-sdk, prometheus-fastapi-instrumentator

## Side by side

| | microduck | vllm |
|---|---|---|
| Size | 157,955 lines written, 206 code files | 2,426,215 lines written, 3,378 code files |
| Who writes it | 25.8% of its commits signed by AI. With Claude Code and Codex | 13.4% 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 9, 2026, 1,081 commits, 13,619 stars | Last push November 9, 2026, 24,920 commits, 96,584 stars |
| Tests | 19 test files. 1.5% of its code files have a test that imports them | 2,469 test files. 60.9% 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, microduck or vllm?

vllm, with 2,426,215 lines written; microduck has 157,955.

The proof: [vllm-project/vllm's code at commit 821851e](https://github.com/vllm-project/vllm/tree/821851eab038d2ec1bcdcb8c7da32a3728f71358)

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

vllm, with 96,584 stars; microduck has 13,619.

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

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

vllm, with 2,469 test files; microduck has 19.

The proof: [vllm-project/vllm's code at commit 821851e](https://github.com/vllm-project/vllm/tree/821851eab038d2ec1bcdcb8c7da32a3728f71358)

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

Both got their last push on November 9, 2026.

The proof: [pollen-robotics/microduck's commits on GitHub](https://github.com/pollen-robotics/microduck/commits)

### Which has more commits signed by AI, microduck or vllm?

microduck: an AI signed 25.8% of its commits, with Claude Code and Codex; in vllm, 13.4%.

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

## Sources

- pollen-robotics/microduck: Read on November 9, 2026, at commit da34a22 (https://github.com/pollen-robotics/microduck/tree/da34a2212ae12eddfd73d0dfbf924f291aaf1dc9)
- vllm-project/vllm: Read on November 9, 2026, at commit 821851e (https://github.com/vllm-project/vllm/tree/821851eab038d2ec1bcdcb8c7da32a3728f71358)

## 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.