outlines vs vllm
outlines and vllm share 6 technologies: mkdocs-material, outlines-core, pillow, jinja2, Pydantic, and jsonschema. Both are written in Python.
What they share and what sets them apart
dottxt-ai
outlines
Structured Outputs
Python16kRead on November 7, 2026, at commit c52af84What is outlines built with?Only in outlines
- diskcache
- genson
In common
mkdocs-material
outlines-core
pillow
- jinja2
- Pydantic
- jsonschema
vllm-project
vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
Python96.6kRead on November 9, 2026, at commit 821851eWhat is vllm built with?Only in vllm
- FastAPI
- axum
- gitdb
- pyzmq
- Hugging Face
- Tokio
starlette
- Ray
- AIOHTTP
- tower
- 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
- 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
- image
minijinja
- torchcodec
minijinja-contrib
- annotated-types
msgspec
validator
- pydantic-core
- opentelemetry-api
- opentelemetry-semantic-conventions-ai
- python-json-logger
- vllm-metrics
- vllm-tracing
tracing
- prometheus-client
psutil
tracing-futures
tracing-subscriber
- model-hosting-container-standards
- OpenTelemetry
opentelemetry-sdk
- prometheus-fastapi-instrumentator
Side by side
outlinesvllm
SizeLines written by people and agents, without generated ones; code files, without tests.
outlines26,890 lines written46 code files
vllm2,426,215 lines written3,378 code files
Who writes itA commit counts as AI's when it carries its signature: a Co-Authored-By line, its author name or the merge of its branch.
outlines0.8% of its commits signed by AIWith Claude Code and GitHub Copilot
vllm13.4% of its commits signed by AIWith Claude Code, Codex, Gemini CLI, Cursor, GitHub Copilot, Devin, Mistral Vibe, CodeRabbit, Factory, and Qwen Code
ActivityFrom GitHub and its history, on the day SeeRepo read it.
outlinesLast push September 21, 20261,324 commits16,005 stars
vllmLast push November 9, 202624,920 commits96,584 stars
TestsThe files that test the code, and the share of code files a test imports.
outlines59 test files84.8% of its code files have a test that imports them
vllm2,469 test files60.9% of its code files have a test that imports them
Frequently asked questions
Which is bigger, outlines or vllm?
vllm, with 2,426,215 lines written; outlines has 26,890.
The proof: vllm-project/vllm's code at commit 821851e
Which has more GitHub stars, outlines or vllm?
vllm, with 96,584 stars; outlines has 16,005.
The proof: vllm-project/vllm on GitHub
Which has more tests, outlines or vllm?
vllm, with 2,469 test files; outlines has 59.
The proof: vllm-project/vllm's code at commit 821851e
Which was updated more recently, outlines or vllm?
vllm: its last push was on November 9, 2026, and outlines's on September 21, 2026.
The proof: vllm-project/vllm's commits on GitHub
Which has more commits signed by AI, outlines or vllm?
vllm: an AI signed 13.4% of its commits, with Claude Code, Codex, Gemini CLI, Cursor, GitHub Copilot, Devin, Mistral Vibe, CodeRabbit, Factory, and Qwen Code; in outlines, 0.8%.
The proof: the commits each tool signed in vllm-project/vllm
See inside your code, today.
Paste your repo and see it drawn, part by part: a medium one in under a minute.
Free, no account.

