Serverless Machine Learning

The Infrastructure-less MLOps

A community for building Machine Learning
(ML) systems using Python and MLOps best practices.

Machine Learning Apps

A currated look at tools, products, ideas and projects built with serverless Machine Learning (ML)

Green Cloud Computing

Green Cloud is a subscription service for software services to perform cloud computing tasks such as Function As A Service, Storage and Database.

https://www.greencloudcomputing.io/
Compute
Sumatra

Sumatra gives teams building AI-driven apps a simple solution to ship and iterate fast without sacrificing security, customization, or scale.

https://sumatra.ai/
Compute
Streaming
Beam

Develop on serverless GPUs, deploy highly performant APIs, and rapidly prototype cloud applications — without managing any infrastructure.

https://www.beam.cloud/
GPUs
Model Serving
ML Development
Pinecone

The Pinecone vector database makes it easy to build high-performance vector search applications. Developer-friendly, fully managed, and easily scalable without infrastructure hassles.

https://www.pinecone.io/
State
Vector Database
WhyLabs

Enable MLOps with cloud-agnostic model monitoring and data monitoring via the WhyLabs AI Observability Platform. Supports any data, at any scale.

https://whylabs.ai/
State
Monitoring
Gantry

Gantry helps you improve your ML products with analytics, alerting, and human feedback.

https://gantry.io/
State
Monitoring
Arize

Increase model velocity and improve AI outcomes with Arize AI’s ML observability platform. Discover issues, diagnose problems, and improve performance.

https://arize.com/
State
Monitoring
Azure ML

Build machine learning models in a simplified way with machine learning platforms from Azure. Machine learning as a service increases accessibility and efficiency.

https://azure.microsoft.com/en-us/products/machine-learning/
State
Model Serving
Cerebrium

Cerebrium makes it easy to launch machine learning models in the cloud and scale up as you grow – with serverless GPU’s, model versioning, shadow deployments and more.

https://www.cerebrium.ai/
State
Model Serving
SageMaker

Build, train, and deploy machine learning (ML) models for any use case with fully managed infrastructure, tools, and workflows.

https://aws.amazon.com/sagemaker/
State
Model Serving
Model Registry
Banana

Banana provides inference hosting on serverless GPUs for machine learning models. It allows you to deploy in three easy steps and a single line of code.

https://www.banana.dev/
State
Model Serving
Valohai

An MLOps platform purpose-built for Pioneers. With Valohai, ML Pioneers push machine learning to completely new frontiers.

https://valohai.com/
ML Development
Experiments
Neptune AI

Manage all your model-building metadata in a single place. Track experiments, register models, integrate with any MLOps tool stack.

https://neptune.ai/
ML Development
Experiments
Comet ML

Track, compare, and reproduce your ML experiments with Comet's machine learning platform. Leverage insights to build better models, faster.

https://www.comet.com/site/
ML Development
Experiments
Weights & Biases

WandB is a central dashboard to keep track of your hyperparameters, system metrics, and predictions so you can compare models live, and share your findings.

https://wandb.ai/site
ML Development
Experiments
State
Model Registry
Train ML

A GPU-enabled Deep Learning Model Training and Hyperparameter platform that lets you start training models on GPUs without the fuss of server management, SSH tunnelling, or data and library management gymnastics.

https://www.trainml.ai/
ML Development
GPUs
Streamlit

Streamlit is an open-source app framework for Machine Learning and Data Science teams.

https://streamlit.io/
Compute
User Interface
Github Pages

GitHub Pages is a static site hosting service that takes HTML, CSS, and JavaScript files straight from a repository on GitHub, optionally runs the files through a build process, and publishes a website.

https://pages.github.com/
Compute
User Interface
Amazon EMR

Amazon EMR is a cloud big data platform for running large-scale distributed data processing jobs, interactive SQL queries, and machine learning applications using open-source analytics frameworks such as Apache Spark, Apache Hive, and Presto.

https://aws.amazon.com/emr/
Compute
Spark
GCP Dataproc

Dataproc is a fully managed and highly scalable service for running Apache Hadoop, Apache Spark, Apache Flink, Presto, and 30+ open source tools and frameworks.

https://cloud.google.com/dataproc
Compute
Spark
Chalice

Chalice is a framework for writing serverless apps in python. It allows you to quickly create and deploy applications that use AWS Lambda.

https://github.com/aws/chalice
Compute
Python
GCP Cloud Run

A fully managed compute platform that automatically scales containers. Build apps in your favorite language and deploy them in seconds.

https://cloud.google.com/run
Compute
Python
Immerok

Immerok is a leading contributor to Apache Flink®, building a new, fully managed Apache Flink cloud service for real-time stream processing apps at any scale.

https://www.immerok.io/
Compute
Streaming
GCP Workflows

Workflows is a fully-managed orchestration platform that executes services in an order that you define: a workflow.

https://cloud.google.com/workflows/
Compute
Orchestration
AWS Step Functions

AWS Step Functions is a visual workflow service that helps developers use AWS services to build distributed applications, automate processes, orchestrate microservices, and create data and machine learning (ML) pipelines.

https://aws.amazon.com/step-functions/
Compute
Orchestration
Hopsworks

A python-centric feature store with the most complete MLOps capabilities. Collaborate and create an effective pipeline on all of your AI data, and bring your models to production.

https://www.hopsworks.ai/
State
Feature Store
Model Serving
Model Registry
Amazon S3

A cloud object storage with industry-leading scalability, data availability, security, and performance.

https://aws.amazon.com/s3/
Data Warehouse
Object Store
Azure Synapse Analytics

A limitless analytics service that brings together data integration, enterprise data warehousing, and big data analytics.

https://azure.microsoft.com/en-us/products/synapse-analytics/#overview
Data Warehouse
Google Cloud Storage

Cloud Storage is a managed service for storing unstructured data. Store any amount of data and retrieve it as often as you like.

https://cloud.google.com/storage
Data Warehouse
Google BigQuery

BigQuery is a serverless, cost-effective and multicloud data warehouse designed to help you turn big data into valuable business insights.

https://cloud.google.com/bigquery
Data Warehouse
Databricks

Databricks combines data warehouses & data lakes into a lakehouse architecture.

https://www.databricks.com/
Data Warehouse
Compute
Spark
State
Model Serving
Snowflake

A single, global platform that powers the Data Cloud. Snowflake is uniquely designed to connect businesses globally, across any type or scale of data and many different workloads, and unlock seamless data collaboration.

https://www.snowflake.com/
Data Warehouse
Amazon Redshift

A fully managed, petabyte-scale data warehouse service in the cloud.

https://aws.amazon.com/redshift/
Data Warehouse
Azure Delta Lake Storage

Delta Lake is an open-source storage layer that brings ACID (atomicity, consistency, isolation, and durability) transactions to Apache Spark and big data workloads.

https://delta.io/
Data Warehouse
Object Store
Hugging Face

Tools for building applications using machine learning.

https://huggingface.co/
Compute
User Interface
State
Model Serving
Model Registry
Decodable

Decodable is a real-time stream processing platform.

https://www.decodable.co/
Compute
Streaming
Modal

Modal lets you run or deploy machine learning models, massively parallel compute jobs, task queues, web apps, and much more, without your own infrastructure.

https://modal.com/
Compute
Orchestration
Python
ML Development
GPUs

Join the Serverless ML Movement

Join our community dedicated to Serverless Machine Learning and take your skills to the next level. Focus on building and making operational ML models without the hassle of managing infrastructure. Connect with like-minded practitioners and learn from each other in this dynamic community.