What is vllm-omni built with?

vllm-omni is a Python repo built with FastAPI, werkzeug, and AIOHTTP. It uses AI through accelerate, auto-round-lib, facexlib, fairscale, filterpy, and 33 more, makes its content with markdown, markdown-it-py, markupsafe, mdurl, tifffile, and 5 more, validates its data with Pydantic and msgspec, is tested with Pytest, datasets, and peft, runs in production with opentelemetry-exporter-http-transport, opentelemetry-exporter-otlp-common, opentelemetry-exporter-prometheus, opentelemetry-semantic-conventions, opentelemetry-semantic-conventions-ai, and 3 more, and uses lmdb, pyarrow, tensorboard-data-server, pyzmq, and Hugging Face. It has 1,649,609 written lines, with 2,401 test files.

Read on November 18, 2026, at commit 07dd3d0. Read it as markdown

The card says what it's built with. Its whole map opens it up: every part of the code and how it connects to the rest.

Frontend

Backend

The base 1

Data 4

AI 38

26 more

Services 1

Support

The base 2

Content 10

Validation 2

Testing 3

Deploy 8

Tools 20

  • antlr4-python3-runtime
  • Numba
  • pre-commit
  • pygments
  • python-discovery
  • Ruff
  • Setuptools
  • tensorboard
  • virtualenv
  • typing-extensions17 files
  • packaging6 files
  • cfgv
8 more
  • clip
  • distlib
  • fire
  • identify
  • iniconfig
  • nodeenv
  • pluggy
  • yapf

Other 58

  • NumPy293 files
  • omegaconf18 files
  • SciPy8 files
  • tqdm7 files
  • filelock3 files
  • pyyaml3 files
  • msgpack1 file
  • pandas1 file
  • prettytable1 file
  • pydantic-settings1 file
  • SymPy1 file
  • absl-py
46 more
  • attrs
  • certifi
  • fsspec
  • future
  • hf-xet
  • lazy-loader
  • networkx
  • nvidia-nccl-cu12
  • opencv-python-headless
  • opentelemetry-exporter-otlp-proto-common
  • platformdirs
  • portalocker
  • python-dateutil
  • termcolor
  • urllib3
  • regex50 files
  • soundfile14 files
  • janus5 files
  • inflect2 files
  • aenum1 file
  • requests1 file
  • tabulate1 file
  • addict
  • aiohappyeyeballs
  • aiosignal
  • charset-normalizer
  • dill
  • easydict
  • frozenlist
  • ftfy
  • grpcio
  • idna
  • iopath
  • kiwisolver
  • mpmath
  • multidict
  • multiprocess
  • propcache
  • protobuf
  • pyparsing
  • six
  • soxr
  • wcwidth
  • xxhash
  • yacs
  • yarl

Other repos with a similar stack

Ordered by how much of its stack they share with vllm-omni, then by stars.

Frequently asked questions

What language is vllm-omni written in?
vllm-omni is written in Python, with 1,649,609 written lines.
What framework does vllm-omni use?
vllm-omni is built with FastAPI, werkzeug, and AIOHTTP.
Does vllm-omni use AI?
Yes. vllm-omni uses AI through accelerate, auto-round-lib, facexlib, fairscale, filterpy, fvcore, gguf, llvmlite, lmcache, NVIDIA, nvidia-cudnn-cu12, nvidia-cudnn-cu13, onnxruntime-rocm, open-clip-torch, openai-whisper, qwen-vl-utils, scikit-image, timm, torchsde, trl, torch, transformers, diffusers, safetensors, einops, torchaudio, cache-dit, torchvision, triton, onnxruntime, opencv-python, x-transformers, tokenizers, s3tokenizer, kernels, sentencepiece, bitsandbytes, and torchada.
What services does vllm-omni use?
vllm-omni uses lmdb, pyarrow, tensorboard-data-server, pyzmq, and Hugging Face.
Does vllm-omni have tests?
Yes. vllm-omni has 2,401 test files and is tested with Pytest, datasets, and peft.
Which repos have a stack like vllm-omni's?
The ones that share most of its stack:ray-project/rayonyx-dot-app/onyxmudler/LocalAI

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.Private repo? Sign in with GitHub

Or look inside SeeRepo's own →

Is it your repo? Add its badge, keep it up to date or take it down →