Neuron PNG and SVG Icon
AWS Neuron is a software development kit (SDK) that enables running high-performance ML models on AWS Inferentia-based instances.
Last Modified: August 29, 2025
16px
32px
48px
64px
Details
Key Features
- SDK for running ML inference on AWS Inferentia and Trainium chips.
- Optimizes models for low-latency, high-throughput inference.
- Supports TensorFlow, PyTorch, and MXNet.
- Integrates with SageMaker and EC2.
Common Use Cases
- Optimizing AI models for AWS Inferentia hardware
- Reducing inference latency for deep learning models
- Running AI workloads on cost-efficient custom chips
Explore More Icons
FSx for NetApp ONTAP
Amazon FSx for NetApp ONTAP offers fully managed NetApp file systems on AWS with familiar features like snapshots, clones, and data tiering.
Keyspaces
Amazon Keyspaces is a scalable, highly available, and managed Apache Cassandra-compatible database service.
File Cache
AWS File Cache is a high-speed cache on AWS for frequently accessed file data stored in disparate sources such as on-premises file systems or S3.
Kinesis Video Streams
Amazon Kinesis Video Streams is a service for securely ingesting, storing, and processing video streams for analytics and machine learning.
Migration Hub
AWS Migration Hub provides a central place to track the progress of application migrations across multiple AWS and partner tools.
Volume
Volume refers to block storage resources like EBS volumes that can be attached to EC2 instances for durable, low-latency storage.
B2B Data Interchange
AWS B2B Data Interchange facilitates secure, scalable exchange of business-to-business data across different organizations using AWS services and custom integrations.
MemoryDB
Amazon MemoryDB for Redis is a Redis-compatible, in-memory database service designed for ultra-fast performance and durability.
RoboMaker
AWS RoboMaker is a service for developing, simulating, and deploying robotic applications using Robot Operating System (ROS) with cloud scalability.
EMR Engine
Amazon EMR Engine is the processing engine component within Amazon EMR that enables scalable, distributed big data processing using frameworks like Spark and Hadoop.
IoT FleetWise
AWS IoT FleetWise is a service that enables automakers to collect, transform, and transfer vehicle data to the cloud in near real time.
Oracle Database at AWS
Oracle Database at AWS enables you to run Oracle databases in the cloud with flexible deployment options, including Amazon RDS and custom EC2 instances.
Private 5G
AWS Private 5G enables you to set up and scale your own private cellular network with plug-and-play hardware and software.
Kinesis Data Streams
Amazon Kinesis Data Streams is a service for building real-time data streaming applications that can continuously ingest and process large volumes of data.
Managed Streaming for Apache Kafka
Amazon MSK (Managed Streaming for Apache Kafka) is a fully managed service for building and running applications using Apache Kafka on AWS.
Cost Explorer
AWS Cost Explorer is a tool that helps you visualize, understand, and manage your AWS costs and usage over time through interactive charts and reports.
Managed Service for Apache Flink
Amazon Managed Service for Apache Flink is a fully managed service for building and running real-time stream processing applications using Apache Flink.
Transcribe
Amazon Transcribe is an automatic speech recognition (ASR) service that converts speech into text for applications like subtitles and transcription.
Application Migration Service
AWS Application Migration Service (MGN) simplifies and accelerates the migration of physical, virtual, or cloud-based servers to AWS with minimal downtime.
Outposts family
AWS Outposts family consists of fully managed solutions that extend AWS infrastructure, services, and tools to on-premises locations for a hybrid cloud experience.
Chime
Amazon Chime is a communication service that enables online meetings, video conferencing, and business calls through a secure and scalable platform.
Fraud Detector
Amazon Fraud Detector is a service that uses machine learning to identify potentially fraudulent online activities in real time.
Apache MXNet on AWS
Apache MXNet on AWS is a scalable deep learning framework optimized for performance and training on AWS infrastructure.
Security Hub
AWS Security Hub provides a comprehensive view of your security state in AWS by aggregating, organizing, and prioritizing security alerts and findings.