[0.0.25] - 2025-09-01
Added
- Deployment Management: Added comprehensive deployment management through CLI
- Dedicated Deployments: Support for creating, managing, and deploying dedicated model instances
- Hardware Management: CLI commands to list and manage GPU/hardware configurations
- Enhanced CLI: Updated CLI usage with deployment commands
Enhanced
- CLI Interface: Enhanced CLI with deployment management capabilities
- Documentation: Updated all documentation to include deployment management examples
[0.0.24] - 2025-08-28
Changed
- Updated CLI usage patterns
- Documentation improvements
[0.0.18] - 2025-08-24
Added
- Completions Endpoint: Added support for text completions with prompt-based generation
- CLI Support for Completions: Extended command-line interface to support completions mode
- Streaming Completions: Added real-time streaming support for text completions
- Async Completions: Full async/await support for completions endpoint
Enhanced
- CLI Interface: Enhanced CLI with
--mode completions and --prompt parameters
- Type Safety: Added type hints for completions responses and parameters
[0.0.4] - 2024-08-05
Added
- Initial Release: Initial release with core functionality
- OpenAI Compatibility: Basic OpenAI compatibility layer
- Authentication: Authentication system
- Chat Completions: Chat completions with message-based conversations
- Embeddings: Text embeddings for semantic search and similarity
- Streaming: Real-time response streaming for chat completions
- Async Support: Full asynchronous support with async/await
- Function Calling: Tool integration and function calling capabilities
- CLI Interface: Command-line interface for quick testing
- Type Safety: Complete type hints for better development experience
- Error Handling: Comprehensive exception handling