Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.

The set of CPU/GPU optimised regularisation modules for iterative image reconstruction and other image processing tasks

Decompose images into components containing structures of different sizes by solving a modified version of the diffusion equatin

Estimate the average ISM properties with Av-PDFs

A projection-based framework for gradient-free and parallel learning