Source: https://seerepo.com/compare/OpenPipe/ART/vs/vllm-project/vllm
Markdown source: https://seerepo.com/compare/OpenPipe/ART/vs/vllm-project/vllm.md
Description: ART and vllm share 11 technologies: FastAPI, OpenAI, AIOHTTP, apache-tvm-ffi, flashinfer-python, NVIDIA, quack-kernels, torch, transformers, Pydantic, and msgspec. Both are written in Python.

# ART vs vllm

ART and vllm share 11 technologies: FastAPI, OpenAI, AIOHTTP, apache-tvm-ffi, flashinfer-python, NVIDIA, quack-kernels, torch, transformers, Pydantic, and msgspec. Both are written in Python.

- [OpenPipe/ART](https://seerepo.com/r/OpenPipe/ART): Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and more!
- [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: FastAPI, OpenAI, AIOHTTP, apache-tvm-ffi, flashinfer-python, NVIDIA, quack-kernels, torch, transformers, Pydantic, msgspec
- Only in ART: Anthropic, weave, causal-conv1d, flash-attn-4, flash-linear-attention, megatron-core, ml-dtypes, torchtune, unsloth-zoo, litellm, peft
- Only in vllm: axum, gitdb, pyzmq, Hugging Face, Tokio, starlette, Ray, tower, mkdocs-material, indicatif, AMD, auto-round-lib, conch-triton-kernels, cuda-bindings, cuda-python, cupy-cuda12x, cupy-cuda13x, humming-kernels, lm-format-enforcer, mooncake-transfer-engine, mooncake-transfer-engine-rocm, nvidia-cudnn-frontend, openai-harmony, oss-harmony, sentencepiece, vllm-bench, vllm-chat, vllm-engine-core-client, vllm-llm, vllm-managed-engine, vllm-parser, vllm-proto, vllm-server, vllm-text, vllm-tokenizer, xgrammar-structural-tag, einops, llm-multimodal, compressed-tensors, safetensors, triton, mistral-common, xgrammar, partial-json-parser, torchvision, 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, image, jinja2, minijinja, torchcodec, minijinja-contrib, annotated-types, validator, opentelemetry-semantic-conventions-ai, python-json-logger, vllm-metrics, vllm-tracing, tracing, prometheus-client, psutil, tracing-subscriber, tracing-futures, model-hosting-container-standards, OpenTelemetry, prometheus-fastapi-instrumentator, tracing-log

## Side by side

| | ART | vllm |
|---|---|---|
| Size | 345,462 lines written, 415 code files | 2,489,750 lines written, 3,450 code files |
| Who writes it | 6.6% of its commits signed by AI. With Claude Code, Cursor, Codex, and Amp | 14% 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 10, 2026, 1,465 commits, 10,856 stars | Last push November 12, 2026, 25,200 commits, 96,790 stars |
| Tests | 391 test files. 49.2% of its code files have a test that imports them | 2,521 test files. 61.1% 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, ART or vllm?

vllm, with 2,489,750 lines written; ART has 345,462.

The proof: [vllm-project/vllm's code at commit c6573ee](https://github.com/vllm-project/vllm/tree/c6573eed5e56fd39b01d610db04616ed9b221851)

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

vllm, with 96,790 stars; ART has 10,856.

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

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

vllm, with 2,521 test files; ART has 391.

The proof: [vllm-project/vllm's code at commit c6573ee](https://github.com/vllm-project/vllm/tree/c6573eed5e56fd39b01d610db04616ed9b221851)

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

vllm: its last push was on November 12, 2026, and ART's on November 10, 2026.

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

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

vllm: an AI signed 14% of its commits, with Claude Code, Codex, Gemini CLI, Cursor, GitHub Copilot, Devin, Mistral Vibe, CodeRabbit, Factory, and Qwen Code; in ART, 6.6%.

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

## Sources

- OpenPipe/ART: Read on November 13, 2026, at commit 534620a (https://github.com/OpenPipe/ART/tree/534620a41b82ed89667f4642cc0b8e1d00e2269b)
- vllm-project/vllm: Read on November 12, 2026, at commit c6573ee (https://github.com/vllm-project/vllm/tree/c6573eed5e56fd39b01d610db04616ed9b221851)

## 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.