v0.1.0 - Initial Release

🎉 Initial Release of Cortex LLM

Features

• Ollama integration for model management
• GPU auto-detection (NVIDIA/AMD)
• CUDA setup automation
• Model download and management
• llama.cpp backend support
• Streaming inference responses
• Context window management
• Memory optimization for large models
• Prompt templates system
• Batch inference mode

Installation

pip install -e .

Documentation

See README.md

Full Changelog: https://github.com/cortexlinux/cortex-llm/commits/v0.1.0