Average Ratings 0 Ratings

Total
ease
features
design
support

No User Reviews. Be the first to provide a review:

Write a Review

Average Ratings 0 Ratings

Total
ease
features
design
support

No User Reviews. Be the first to provide a review:

Write a Review

Description

Joyent offers a Single Tenant Public Cloud that combines the robust security, cost efficiency, and management capabilities of a private cloud. This service is entirely managed by Joyent, ensuring that users have complete control over their private cloud environment, along with comprehensive installation, onboarding, and support services. Customers can opt for either open-source or commercial assistance for their on-premises, user-managed private clouds. The infrastructure is designed to efficiently deliver virtual machines, containers, and bare metal resources, while being capable of handling workloads at an exabyte scale. Joyent’s engineering team provides extensive support for contemporary application frameworks, including microservices, APIs, development tools, and container-native DevOps practices. Triton is a hybrid, modern, and open solution specifically optimized to host the most substantial cloud-native applications. With Joyent, users can expect not only cutting-edge technology but also a partnership that supports their long-term growth and innovation.

Description

The NVIDIA Triton™ inference server provides efficient and scalable AI solutions for production environments. This open-source software simplifies the process of AI inference, allowing teams to deploy trained models from various frameworks, such as TensorFlow, NVIDIA TensorRT®, PyTorch, ONNX, XGBoost, Python, and more, across any infrastructure that relies on GPUs or CPUs, whether in the cloud, data center, or at the edge. By enabling concurrent model execution on GPUs, Triton enhances throughput and resource utilization, while also supporting inferencing on both x86 and ARM architectures. It comes equipped with advanced features such as dynamic batching, model analysis, ensemble modeling, and audio streaming capabilities. Additionally, Triton is designed to integrate seamlessly with Kubernetes, facilitating orchestration and scaling, while providing Prometheus metrics for effective monitoring and supporting live updates to models. This software is compatible with all major public cloud machine learning platforms and managed Kubernetes services, making it an essential tool for standardizing model deployment in production settings. Ultimately, Triton empowers developers to achieve high-performance inference while simplifying the overall deployment process.

API Access

Has API No 

API Access

Has API No 

Screenshots View All

Screenshots View All

Integrations

Alibaba CloudAP No 
Amazon EKS No 
Amazon SageMaker No 
Azure Kubernetes Service (AKS) No 
Azure Machine Learning No 
FauxPilot No 
Google Kubernetes Engine (GKE) No 
HPE Ezmeral No 
Kubernetes No 
LiteLLM No 
MXNet No 
NVIDIA DeepStream SDK No 
NVIDIA Morpheus No 
Open Container Initiative (OCI) Yes 
Prometheus No 
PyTorch No 
Tencent Cloud No 
TensorFlow No 
Thunder Compute No 
cloud-init Yes 

Integrations

Alibaba CloudAP Yes 
Amazon EKS Yes 
Amazon SageMaker Yes 
Azure Kubernetes Service (AKS) Yes 
Azure Machine Learning Yes 
FauxPilot Yes 
Google Kubernetes Engine (GKE) Yes 
HPE Ezmeral Yes 
Kubernetes Yes 
LiteLLM Yes 
MXNet Yes 
NVIDIA DeepStream SDK Yes 
NVIDIA Morpheus Yes 
Open Container Initiative (OCI) No 
Prometheus Yes 
PyTorch Yes 
Tencent Cloud Yes 
TensorFlow Yes 
Thunder Compute Yes 
cloud-init No 

Pricing Details

No price information available.
Free Trial No 
Free Version No 

Pricing Details

Free
Free Trial No 
Free Version Yes 

Deployment

Web-Based No 
On-Premises Yes 
iPhone App No 
iPad App No 
Android App No 
Windows No 
Mac No 
Linux No 
Chromebook No 

Deployment

Web-Based No 
On-Premises No 
iPhone App No 
iPad App No 
Android App No 
Windows Yes 
Mac Yes 
Linux Yes 
Chromebook No 

Customer Support

Business Hours Yes 
Live Rep (24/7) No 
Online Support Yes 

Customer Support

Business Hours Yes 
Live Rep (24/7) No 
Online Support Yes 

Types of Training

Training Docs No 
Webinars No 
Live Training (Online) Yes 
In Person Yes 

Types of Training

Training Docs Yes 
Webinars No 
Live Training (Online) No 
In Person Yes 

Vendor Details

Company Name

Joyent

Founded

2004

Country

United States

Website

www.joyent.com

Vendor Details

Company Name

NVIDIA

Country

United States

Website

developer.nvidia.com/nvidia-triton-inference-server

Product Features

Container Management

Access Control No 
Application Development No 
Automatic Scaling No 
Build Automation No 
Container Health Management No 
Container Storage No 
Deployment Automation No 
File Isolation No 
Hybrid Deployments No 
Network Isolation No 
Orchestration No 
Shared File Systems No 
Version Control No 
Virtualization No 

Data Center Management

Audit Trail No 
Behavior-Based Acceleration No 
Cross Reference System No 
Device Auto Discovery No 
Diagnostic Testing No 
Import / Export Data No 
JCL Management No 
Multi-Platform Yes 
Multi-User Yes 
Power Management No 
Sarbanes-Oxley Compliance No 

Product Features

Artificial Intelligence

Chatbot No 
For Healthcare No 
For Sales No 
For eCommerce No 
Image Recognition No 
Machine Learning No 
Multi-Language No 
Natural Language Processing No 
Predictive Analytics No 
Process/Workflow Automation No 
Rules-Based Automation No 
Virtual Personal Assistant (VPA) No 

Machine Learning

Deep Learning No 
ML Algorithm Library No 
Model Training No 
Natural Language Processing (NLP) No 
Predictive Modeling No 
Statistical / Mathematical Tools No 
Templates No 
Visualization No 

Alternatives

Alternatives

NVIDIA NIM Reviews

NVIDIA NIM

NVIDIA