One-Click
AI Deployments
Deploy popular AI frameworks, inference servers, and ML tools with a single click. Pre-configured, GPU-optimized, and production-ready.
Pre-Configured AI Applications for Instant Deployment
SLYD's App Marketplace offers 50+ pre-configured AI applications ready for one-click deployment. Deploy ML frameworks, inference servers, development environments, and MLOps tools on your infrastructure—whether that's SLYD cloud compute, your own hardware, or a hybrid setup.
What's Available
Our app library covers the complete AI development lifecycle:
ML Frameworks
PyTorch, TensorFlow, JAX, and Hugging Face Transformers with CUDA and cuDNN pre-configured
Inference Servers
vLLM, Text Generation Inference (TGI), NVIDIA Triton, Ollama, and TensorRT-LLM optimized for production serving
Notebooks & IDEs
JupyterHub, JupyterLab, VS Code Server, and RStudio with persistent storage and GPU access
MLOps Tools
MLflow, Weights & Biases, Ray, DVC, Airflow, and Prefect for experiment tracking and orchestration
Data & Monitoring
PostgreSQL, Redis, MinIO, Prometheus, Grafana, and DCGM Exporter for observability
Why Use Pre-Configured Apps?
Skip the infrastructure setup and start building immediately.
Time Savings
Pre-configured apps eliminate hours of driver installation, dependency management, and configuration tuning. Deploy production-ready environments in minutes.
Consistency
Every deployment uses tested configurations with compatible versions of CUDA, drivers, and libraries. No more debugging dependency conflicts.
Security
All applications are scanned for vulnerabilities and updated regularly. Enterprise plans include additional security controls and compliance documentation.
Data Sovereignty
Applications run on your chosen infrastructure—SLYD cloud, your private data center, or hybrid deployments. Your data never leaves your control.
Why SLYD
Every app in our marketplace includes:
- Optimized — GPU drivers, CUDA versions, and dependencies tuned for performance
- Secured — Vulnerability scanning and regular security updates
- Supported — Enterprise plans include direct support for marketplace apps
- Persistent — Workspaces and data persist across sessions
Need a Custom App?
Bring your own Docker containers or request a custom template from our team.
Contact UsMost Popular Apps
Production-ready templates for our growing community of AI developers
Code Server
This app provisions a secure, cloud-hosted development environment that runs code-server (VS Code in...
SystemMonitor
System Monitoring
VLLM Inference Engine (UI)
Pre-configured and ready for deployment.
Qwen2.5-7B-Instruct Inference Engine
Qwen2.5-7B-Instruct is an instruction-tuned transformer (~7.6B params) built for helpful dialogue, t...
N8N
n8n is an open-source workflow automation tool that lets you connect apps, APIs, and databases throu...
Oobabooga
oobabooga (Text-Generation-WebUI) is an open-source, ChatGPT-style interface for running large langu...
Training & Development
PyTorch
Deep learning framework
TensorFlow
ML platform
JAX
High-performance ML
Transformers
Hugging Face library
DeepSpeed
Training optimization
FSDP
Fully sharded training
Production Serving
vLLM
High-throughput LLM serving
TGI
Text Generation Inference
Triton
NVIDIA inference server
Ollama
Local LLM serving
TensorRT-LLM
Optimized inference
llama.cpp
CPU/GPU inference
Development Environments
JupyterHub
Multi-user notebooks
VS Code Server
Browser-based IDE
RStudio
R development
JupyterLab
Next-gen notebooks
Experiment & Model Management
MLflow
Experiment tracking
Weights & Biases
ML experiment platform
Ray
Distributed computing
DVC
Data version control
Airflow
Workflow orchestration
Prefect
Data pipelines
Data Processing
PostgreSQL
Relational database
Redis
In-memory data store
MinIO
S3-compatible storage
RAPIDS
GPU data science
Observability
Prometheus
Metrics collection
Grafana
Dashboards & visualization
DCGM Exporter
GPU metrics
Vector
Log aggregation
Enterprise-Ready Deployments
Security Scanned
Every app is scanned for vulnerabilities. Regular updates and patches for all published versions.
Optimized Defaults
GPU drivers, CUDA versions, and library dependencies pre-configured for optimal performance.
Auto-Scaling
Apps automatically scale based on demand. Define scaling policies or let the platform optimize.
Support Included
Enterprise plans include support for all marketplace apps. Direct access to our engineering team.
Need a Custom App?
Bring your own Docker containers or request a custom template. We can help you deploy any workload.
Ready to Deploy?
Sign up and deploy your first app in under 5 minutes. No credit card required to explore.