flyte
knowledge-repo
Our great sponsors
flyte | knowledge-repo | |
---|---|---|
31 | 2 | |
4,727 | 5,432 | |
3.3% | 0.3% | |
9.8 | 4.1 | |
6 days ago | 9 months ago | |
Go | Python | |
Apache License 2.0 | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
flyte
-
First 15 Open Source Advent projects
9. Flyte by Union AI | Github | tutorial
-
Flyte 1.10: Self-hosted solution to build production-grade data and ML pipelines; now ships with monorepo, new agents and sensors, eager workflows and more 🚀 (4.1k stars on GitHub)
GitHub: https://github.com/flyteorg/flyte
-
Flyte: Open-source orchestrator for building production-grade ML pipelines
This is actually but a link to Flyte, this is a link to the documentation for the Flyte integration in LangChain, a separate product.
Flyte's homepage is https://flyte.org/
- Flyte: Advanced workflow orchestration alternative to Apache Airflow
-
Orchestration: Thoughts on Dagster, Airflow and Prefect?
Anyone tried Flyte?
-
Flyte 1.6.0: Self-hosted solution to build production-grade data and ML pipelines; now ships with PyTorch elastic training, image specification without dockerfile, enhanced task execution insights and more 🚀 (3.4k stars on GitHub)
Website: https://flyte.org/
-
Flyte(v1.5.0) - Self-hosted solution to build production-grade data and ML pipelines; now ships with streaming support, pod templates, partial tasks and more 🚀 (3.2k stars on GitHub)
Flyte is an open source orchestration tool for managing the workflow of machine learning and AI projects. It runs on top of Kubernetes.
- Flyte: Open-Source Kubernetes-Native ML Orchestrator Implemented in Go
-
What is MLOps and how to get started? | MLOps series | Deploying ML in production
I have a question though, what is your opinion on https://flyte.org. My pipeline uses this and it’ll be interesting to get your perspectives on it’s capabilities.
-
Github alternative for ML?
Have you looked at flyte.org. It aims to bring "versioning", "compute" and "reproducibility" together in one package.
knowledge-repo
-
How do you document a ML research?
While a start, a few that just being a markdown is editor is not enough, GitHub and GitLab already have this sort of wiki. I feel something like https://github.com/airbnb/knowledge-repo provides a better experience, since it gives an incentive for Data Scientists to make their source notebook well documented, and be a SSoT. With a Wiki like, if you change something on the original project, you need to remind yourself to update your reports. If your notebook is in itself your report, that's not necessary. Plus, it would benefit from the Semantic Diffs that DagsHub already have implemented.
- How does everyone share their models etc. across teams for re-use effectively?
What are some alternatives?
metaflow - :rocket: Build and manage real-life ML, AI, and data science projects with ease!
Apache Superset - Apache Superset is a Data Visualization and Data Exploration Platform [Moved to: https://github.com/apache/superset]
argo - Workflow Engine for Kubernetes
superset - Apache Superset is a Data Visualization and Data Exploration Platform
temporal - Temporal service
akshare - AKShare is an elegant and simple financial data interface library for Python, built for human beings! 开源财经数据接口库 [Moved to: https://github.com/akfamily/akshare]
kubeflow - Machine Learning Toolkit for Kubernetes
scikit-learn - scikit-learn: machine learning in Python
Celery-Kubernetes-Operator - An operator to manage celery clusters on Kubernetes (Work in Progress)
pycm - Multi-class confusion matrix library in Python
Kedro - Kedro is a toolbox for production-ready data science. It uses software engineering best practices to help you create data engineering and data science pipelines that are reproducible, maintainable, and modular.
akshare - AKShare is an elegant and simple financial data interface library for Python, built for human beings! 开源财经数据接口库