Source: https://seerepo.com/compare/ray-project/ray/vs/vllm-project/vllm-omni
Markdown source: https://seerepo.com/compare/ray-project/ray/vs/vllm-project/vllm-omni.md
Description: ray and vllm-omni share 41 technologies: FastAPI, tensorboard-data-server, pyarrow, pyzmq, Hugging Face, werkzeug, AIOHTTP, cycler, fonttools, contourpy, Rich, bitsandbytes, einops, fairscale, llvmlite, onnxruntime, openai-whisper, safetensors, scikit-image, sentencepiece, timm, tokenizers, triton, torch, transformers, torchvision, diffusers, imageio, markdown, markdown-it-py, markupsafe, mdurl, pillow, jinja2, decord, Pydantic, opentelemetry-semantic-conventions, psutil, OpenTelemetry, opentelemetry-exporter-prometheus, and opentelemetry-exporter-otlp-proto-grpc. Both are written in Python.

# ray vs vllm-omni

ray and vllm-omni share 41 technologies: FastAPI, tensorboard-data-server, pyarrow, pyzmq, Hugging Face, werkzeug, AIOHTTP, cycler, fonttools, contourpy, Rich, bitsandbytes, einops, fairscale, llvmlite, onnxruntime, openai-whisper, safetensors, scikit-image, sentencepiece, timm, tokenizers, triton, torch, transformers, torchvision, diffusers, imageio, markdown, markdown-it-py, markupsafe, mdurl, pillow, jinja2, decord, Pydantic, opentelemetry-semantic-conventions, psutil, OpenTelemetry, opentelemetry-exporter-prometheus, and opentelemetry-exporter-otlp-proto-grpc. Both are written in Python.

- [ray-project/ray](https://seerepo.com/r/ray-project/ray): Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
- [vllm-project/vllm-omni](https://seerepo.com/r/vllm-project/vllm-omni): A framework for efficient model inference with omni-modality models

## What they share and what sets them apart

- In common: FastAPI, tensorboard-data-server, pyarrow, pyzmq, Hugging Face, werkzeug, AIOHTTP, cycler, fonttools, contourpy, Rich, bitsandbytes, einops, fairscale, llvmlite, onnxruntime, openai-whisper, safetensors, scikit-image, sentencepiece, timm, tokenizers, triton, torch, transformers, torchvision, diffusers, imageio, markdown, markdown-it-py, markupsafe, mdurl, pillow, jinja2, decord, Pydantic, opentelemetry-semantic-conventions, psutil, OpenTelemetry, opentelemetry-exporter-prometheus, opentelemetry-exporter-otlp-proto-grpc
- Only in ray: aimrecords, aimrocks, amqp, array-record, arro3-core, async-lru, azure-common, azure-datalake-store, azure-storage-blob, confluent-kafka, delta-kernel-rust-sharing-wrapper, diskcache, expiringdict, feather-format, gitdb, google-cloud-core, h5py, huey, jupyter-cache, kombu, partd, petastorm, pickleshare, py-partiql-parser, pylance, pymongo, qpd, s3torchconnectorclient, s3transfer, semidbm, sqlitedict, taskiq, zict, mcap, aioboto3, MongoDB, Redis, adlfs, pyiceberg, smart-open, deltalake, clickhouse-connect, daft, gcsfs, lance-namespace, obstore, Celery, delta-sharing, fastavro, hudi, s3fs, s3torchconnector, taskiq-redis, zarr, Google, Google Cloud Storage, Kafka, Databricks, adagio, asgiref, Flask, flask-cors, graphene, graphql-core, graphql-relay, jupyter-core, jupyterlab-server, pygame, pymars, Ray, starlette, pyspark, Lightning, raydp, anyio, tornado, uvicorn, React, react-router-dom, accessible-pygments, alabaster, jupyterlab-pygments, pydata-sphinx-theme, soupsieve, sphinx-design, tinycss2, aim-ui, alive-progress, bokeh, glfw, halo, jupyter-server-terminals, jupyterlab-widgets, matplotlib-inline, Plotly, prompt-toolkit, pyglet, pyopengl, spinners, Textual, widgetsnbextension, xyzservices, Gradio, ipywidgets, pydot, alembic, peewee, sqlglot, adal, argon2-cffi, argon2-cffi-bindings, azure-identity, flask-basicauth, gcs-oauth2-boto-plugin, google-auth-oauthlib, google-oauth, google-reauth, id, itsdangerous, joserfc, jwcrypto, keyring, msal, msal-extensions, oauth2client, oauthlib, pyjwt, pyu2f, requests-oauthlib, cryptography, google-auth-httplib2, aws-requests-auth, albucore, autograd, ax-platform, bayesian-optimization, botorch, cma, cmdstanpy, crcmod, cupy-cuda100, cupy-cuda12x, cupy-cuda13x, fbgemm-gpu, gpytorch, gradio-client, gym, jaxlib, labmaze, LangChain, lightning-utilities, linear-operator, lm-eval, minigrid, ml-dtypes, moocore, mosaicml, nltk, ONNX, onnx-ir, onnxscript, opt-einsum, optax, orbax-checkpoint, peft, prophet, pymoo, pyro-ppl, pytorch-ranger, rouge-score, sacrebleu, skops, stanio, statsforecast, tf-keras, tiktoken, torch-geometric, torch-optimizer, torch-scatter, torch-sparse, torchtext, yahp, gymnasium, TensorFlow, jax, xgboost, lightgbm, scikit-learn, MLflow, datasets, pytorch-lightning, comet-ml, dm-env, flax, Keras, torchmetrics, aim, ale-py, configspace, deepspeed, dm-control, hpbandster, hyperopt, nevergrad, open-spiel, Optuna, tensorflow-probability, zoopt, bleach, defusedxml, et-xmlfile, imageio-ffmpeg, imagesize, jsonlines, linkify-it-py, lxml, mako, mdit-py-plugins, mistune, moviepy, myst-parser, nbconvert, nh3, openpyxl, pandocfilters, pytablewriter, readme-renderer, ruamel-yaml, ruamel-yaml-clib, strictyaml, tinyscaler, webencodings, xlrd, xmltodict, docutils, beautifulsoup4, nbformat, torchcodec, annotated-types, fastjsonschema, fqdn, jsonschema-path, jsonschema-specifications, openapi-spec-validator, pathvalidate, referencing, rfc3339-validator, rfc3986, rfc3986-validator, typepy, validators, jsonschema, aiobotocore, applicationinsights, aws-sam-translator, aws-xray-sdk, azure-cli-core, azure-cli-telemetry, azure-core, azure-mgmt-compute, azure-mgmt-core, azure-mgmt-network, azure-mgmt-resource, azure-mgmt-resource-deployments, boto, cloud-tpu-diagnostics, colorlog, execnet, google-cloud-audit-log, Gunicorn, log-symbols, ml-goodput-measurement, msrestazure, opencensus-context, opentelemetry-instrumentation, opentelemetry-instrumentation-asgi, opentelemetry-util-http, python-json-logger, supervisor, boto3, botocore, prometheus-client, pybuildkite, kubernetes, docker, opentelemetry-instrumentation-fastapi, ray-haproxy, typeface-roboto, MUI, usehooks-ts, lowlight, react-window, react-icons, @mui/icons-material, js-yaml
- Only in vllm-omni: lmdb, matplotlib, accelerate, auto-round-lib, facexlib, filterpy, fvcore, gguf, lmcache, NVIDIA, nvidia-cudnn-cu12, nvidia-cudnn-cu13, onnxruntime-rocm, open-clip-torch, qwen-vl-utils, torchsde, trl, torchaudio, cache-dit, opencv-python, x-transformers, s3tokenizer, kernels, torchada, tifffile, av, msgspec, opentelemetry-exporter-http-transport, opentelemetry-exporter-otlp-common, opentelemetry-semantic-conventions-ai

## Side by side

| | ray | vllm-omni |
|---|---|---|
| Size | 1,583,573 lines written, 2,829 code files | 1,649,609 lines written, 2,220 code files |
| Who writes it | 3.8% of its commits signed by AI. With Claude Code, Gemini CLI, GitHub Copilot, Cursor, and Codex | 11.7% of its commits signed by AI. With Claude Code, Cursor, GitHub Copilot, Codex, Gemini CLI, and Jules |
| Activity | Last push November 18, 2026, 32,530 commits, 44,318 stars | Last push November 18, 2026, 4,411 commits, 7,828 stars |
| Tests | 2,221 test files. 9.4% of its code files have a test that imports them | 2,401 test files. 70.5% 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, ray or vllm-omni?

vllm-omni, with 1,649,609 lines written; ray has 1,583,573.

The proof: [vllm-project/vllm-omni's code at commit 07dd3d0](https://github.com/vllm-project/vllm-omni/tree/07dd3d0cdea3325d8026a93485b60dfe3be6f29d)

### Which has more GitHub stars, ray or vllm-omni?

ray, with 44,318 stars; vllm-omni has 7,828.

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

### Which has more tests, ray or vllm-omni?

vllm-omni, with 2,401 test files; ray has 2,221.

The proof: [vllm-project/vllm-omni's code at commit 07dd3d0](https://github.com/vllm-project/vllm-omni/tree/07dd3d0cdea3325d8026a93485b60dfe3be6f29d)

### Which was updated more recently, ray or vllm-omni?

Both got their last push on November 18, 2026.

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

### Which has more commits signed by AI, ray or vllm-omni?

vllm-omni: an AI signed 11.7% of its commits, with Claude Code, Cursor, GitHub Copilot, Codex, Gemini CLI, and Jules; in ray, 3.8%.

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

## Sources

- ray-project/ray: Read on November 18, 2026, at commit eb50407 (https://github.com/ray-project/ray/tree/eb50407602c55f2660b4a3a93d7e2fe07824ae20)
- vllm-project/vllm-omni: Read on November 18, 2026, at commit 07dd3d0 (https://github.com/vllm-project/vllm-omni/tree/07dd3d0cdea3325d8026a93485b60dfe3be6f29d)

## 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.
