Repository Showcase
A curated collection of interesting GitHub repositories
lodestone-rock/RamTorch
Trains models exceeding GPU memory
Related repos
- memory operating system for managing AI model memory across tasks and sessions
- Run 70B LLMs on a 4GB GPU with layer-wise inference and memory optimization, quantization optional
- Hardware-accelerated GPU terminal emulator
- open-source memory engine for LLMs and AI agents
- Builds knowledge through conversations with LLMs
- GPU-optimized library for training massive transformer models at scale
- semantic cache for LLM queries, speeds up GPT apps, cuts API costs
- programming language for building lightweight high-performance systems
- open source video generation for low VRAM GPUs
- Open-source tools for running and improving LLM applications—gateway, observability, data feedback, optimization
