v2.4.0May 8, 2026
Vector DB Integration
Introducing native vector database support for RAG applications.
- featureVector database integration with Pinecone, Weaviate, and Qdrant
- featureAutomatic document chunking and embedding
- featureSemantic search API endpoints
- improvement50% faster model cold starts
v2.3.0April 25, 2026
Llama 3.1 Support
Full support for Meta's latest Llama 3.1 model family.
- featureLlama 3.1 8B, 70B, and 405B models in Model Hub
- featureOptimized inference for 405B with tensor parallelism
- improvementUpdated SDK with streaming improvements
- fixFixed memory leak in long-running inference jobs
v2.2.0April 10, 2026
Team Collaboration
New features for team workflows and collaboration.
- featureTeam workspaces with role-based access control
- featureShared deployments and environments
- featureAudit logs for enterprise compliance
- improvementImproved dashboard performance
v2.1.0March 28, 2026
Custom Domains
Deploy your AI applications on your own domain.
- featureCustom domain support with automatic SSL
- featureWildcard subdomain routing
- improvementReduced deployment time by 40%
- fixFixed WebSocket connection stability
v2.0.0March 15, 2026
CloudeUp 2.0
Major platform update with serverless GPU infrastructure.
- featureServerless GPU with automatic scaling
- featurePay-per-token billing model
- featureGlobal edge deployment
- featureNew CLI with improved developer experience
- improvementComplete dashboard redesign
