Source: https://seerepo.com/compare/liguodongiot/llm-action/vs/ray-project/ray
Markdown source: https://seerepo.com/compare/liguodongiot/llm-action/vs/ray-project/ray.md
Description: llm-action and ray share 66 technologies: partd, pickleshare, pyarrow, pyzmq, s3transfer, smart-open, tensorboard-data-server, zict, AIOHTTP, jupyter-core, jupyterlab-server, tornado, werkzeug, cycler, fonttools, jupyterlab-pygments, soupsieve, tinycss2, contourpy, matplotlib-inline, prompt-toolkit, argon2-cffi, argon2-cffi-bindings, Google, google-auth-oauthlib, oauthlib, requests-oauthlib, cupy-cuda12x, deepspeed, llvmlite, nltk, ONNX, rouge-score, scikit-learn, sentencepiece, tokenizers, torchtext, torchvision, triton, xgboost, torch, transformers, beautifulsoup4, bleach, defusedxml, jinja2, lxml, markdown, markdown-it-py, markupsafe, mdit-py-plugins, mdurl, mistune, nbconvert, nbformat, pandocfilters, pillow, webencodings, fastjsonschema, jsonschema, Pydantic, execnet, prometheus-client, psutil, boto3, and botocore. llm-action is written in HTML and ray in Python.

# llm-action vs ray

llm-action and ray share 66 technologies: partd, pickleshare, pyarrow, pyzmq, s3transfer, smart-open, tensorboard-data-server, zict, AIOHTTP, jupyter-core, jupyterlab-server, tornado, werkzeug, cycler, fonttools, jupyterlab-pygments, soupsieve, tinycss2, contourpy, matplotlib-inline, prompt-toolkit, argon2-cffi, argon2-cffi-bindings, Google, google-auth-oauthlib, oauthlib, requests-oauthlib, cupy-cuda12x, deepspeed, llvmlite, nltk, ONNX, rouge-score, scikit-learn, sentencepiece, tokenizers, torchtext, torchvision, triton, xgboost, torch, transformers, beautifulsoup4, bleach, defusedxml, jinja2, lxml, markdown, markdown-it-py, markupsafe, mdit-py-plugins, mdurl, mistune, nbconvert, nbformat, pandocfilters, pillow, webencodings, fastjsonschema, jsonschema, Pydantic, execnet, prometheus-client, psutil, boto3, and botocore. llm-action is written in HTML and ray in Python.

- [liguodongiot/llm-action](https://seerepo.com/r/liguodongiot/llm-action): 本项目旨在分享大模型相关技术原理以及实战经验（大模型工程化、大模型应用落地）
- [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.

## What they share and what sets them apart

- In common: partd, pickleshare, pyarrow, pyzmq, s3transfer, smart-open, tensorboard-data-server, zict, AIOHTTP, jupyter-core, jupyterlab-server, tornado, werkzeug, cycler, fonttools, jupyterlab-pygments, soupsieve, tinycss2, contourpy, matplotlib-inline, prompt-toolkit, argon2-cffi, argon2-cffi-bindings, Google, google-auth-oauthlib, oauthlib, requests-oauthlib, cupy-cuda12x, deepspeed, llvmlite, nltk, ONNX, rouge-score, scikit-learn, sentencepiece, tokenizers, torchtext, torchvision, triton, xgboost, torch, transformers, beautifulsoup4, bleach, defusedxml, jinja2, lxml, markdown, markdown-it-py, markupsafe, mdit-py-plugins, mdurl, mistune, nbconvert, nbformat, pandocfilters, pillow, webencodings, fastjsonschema, jsonschema, Pydantic, execnet, prometheus-client, psutil, boto3, botocore
- Only in llm-action: apex, matplotlib, seaborn, cuda-python, flash-attn, langdetect, librosa, polygraphy, pycocotools, spaCy, spacy-legacy, tensorrt, thinc, transformer-engine, bs4, feedparser, jupytext, newspaper3k, sgmllib3k, spacy-loggers
- Only in ray: FastAPI, 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, petastorm, py-partiql-parser, pylance, pymongo, qpd, s3torchconnectorclient, semidbm, sqlitedict, taskiq, mcap, aioboto3, MongoDB, Redis, adlfs, pyiceberg, clickhouse-connect, daft, deltalake, gcsfs, lance-namespace, obstore, Celery, delta-sharing, fastavro, hudi, s3fs, s3torchconnector, taskiq-redis, zarr, Hugging Face, Google Cloud Storage, Kafka, Databricks, adagio, asgiref, Flask, flask-cors, graphene, graphql-core, graphql-relay, pygame, pymars, Ray, starlette, pyspark, Lightning, raydp, anyio, uvicorn, React, react-router-dom, accessible-pygments, alabaster, pydata-sphinx-theme, sphinx-design, aim-ui, alive-progress, bokeh, glfw, halo, jupyter-server-terminals, jupyterlab-widgets, Plotly, pyglet, pyopengl, spinners, Textual, widgetsnbextension, xyzservices, Gradio, ipywidgets, Rich, pydot, alembic, peewee, sqlglot, adal, azure-identity, flask-basicauth, gcs-oauth2-boto-plugin, google-oauth, google-reauth, id, itsdangerous, joserfc, jwcrypto, keyring, msal, msal-extensions, oauth2client, pyjwt, pyu2f, cryptography, google-auth-httplib2, aws-requests-auth, albucore, autograd, ax-platform, bayesian-optimization, bitsandbytes, botorch, cma, cmdstanpy, crcmod, cupy-cuda100, cupy-cuda13x, einops, fairscale, fbgemm-gpu, gpytorch, gradio-client, gym, jaxlib, labmaze, LangChain, lightning-utilities, linear-operator, lm-eval, minigrid, ml-dtypes, moocore, mosaicml, onnx-ir, onnxruntime, onnxscript, openai-whisper, opt-einsum, optax, orbax-checkpoint, peft, prophet, pymoo, pyro-ppl, pytorch-ranger, sacrebleu, safetensors, scikit-image, skops, stanio, statsforecast, tf-keras, tiktoken, timm, torch-geometric, torch-optimizer, torch-scatter, torch-sparse, yahp, gymnasium, TensorFlow, jax, lightgbm, MLflow, datasets, pytorch-lightning, comet-ml, dm-env, flax, Keras, torchmetrics, aim, ale-py, configspace, diffusers, dm-control, hpbandster, hyperopt, nevergrad, open-spiel, Optuna, tensorflow-probability, zoopt, et-xmlfile, imageio, imageio-ffmpeg, imagesize, jsonlines, linkify-it-py, mako, moviepy, myst-parser, nh3, openpyxl, pytablewriter, readme-renderer, ruamel-yaml, ruamel-yaml-clib, strictyaml, tinyscaler, xlrd, xmltodict, docutils, decord, torchcodec, annotated-types, fqdn, jsonschema-path, jsonschema-specifications, openapi-spec-validator, pathvalidate, referencing, rfc3339-validator, rfc3986, rfc3986-validator, typepy, validators, 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, google-cloud-audit-log, Gunicorn, log-symbols, ml-goodput-measurement, msrestazure, opencensus-context, opentelemetry-instrumentation, opentelemetry-instrumentation-asgi, opentelemetry-semantic-conventions, opentelemetry-util-http, python-json-logger, supervisor, pybuildkite, OpenTelemetry, kubernetes, opentelemetry-exporter-prometheus, docker, opentelemetry-exporter-otlp-proto-grpc, opentelemetry-instrumentation-fastapi, ray-haproxy, typeface-roboto, MUI, usehooks-ts, lowlight, react-window, react-icons, @mui/icons-material, js-yaml

## Side by side

| | llm-action | ray |
|---|---|---|
| Size | 23,875 lines written, 10 code files | 1,566,356 lines written, 2,810 code files |
| Who writes it | 0% of its commits signed by AI | 3.7% of its commits signed by AI. With Claude Code, Gemini CLI, GitHub Copilot, Cursor, and Codex |
| Activity | Last push October 14, 2026, 945 commits, 25,281 stars | Last push November 13, 2026, 32,468 commits, 44,282 stars |
| Tests | 1 test files | 2,208 test files. 9.4% 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, llm-action or ray?

ray, with 1,566,356 lines written; llm-action has 23,875.

The proof: [ray-project/ray's code at commit de4c576](https://github.com/ray-project/ray/tree/de4c5765b6cf0265f43f9edccf5bd3821f3a9468)

### Which has more GitHub stars, llm-action or ray?

ray, with 44,282 stars; llm-action has 25,281.

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

### Which has more tests, llm-action or ray?

ray, with 2,208 test files; llm-action has 1.

The proof: [ray-project/ray's code at commit de4c576](https://github.com/ray-project/ray/tree/de4c5765b6cf0265f43f9edccf5bd3821f3a9468)

### Which was updated more recently, llm-action or ray?

ray: its last push was on November 13, 2026, and llm-action's on October 14, 2026.

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

### Which has more commits signed by AI, llm-action or ray?

ray: an AI signed 3.7% of its commits, with Claude Code, Gemini CLI, GitHub Copilot, Cursor, and Codex.

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

## Sources

- liguodongiot/llm-action: Read on November 16, 2026, at commit d33c2c0 (https://github.com/liguodongiot/llm-action/tree/d33c2c0f06e4d402c669bd57e6506955efbec9ff)
- ray-project/ray: Read on November 13, 2026, at commit de4c576 (https://github.com/ray-project/ray/tree/de4c5765b6cf0265f43f9edccf5bd3821f3a9468)

## 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.
