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

A high-throughput and memory-efficient inference and serving engine for LLMs

Kandinsky conformal prediction for image segmentation algorithms

Use your Neovim like using Cursor AI IDE!

Constrained Empirical Risk Minimization

Vim-fork focused on extensibility and usability

relplot: Utilities for measuring calibration and plotting reliability diagrams

Evaluation framework for oncology foundation models (FMs)

Ahcore is the AI for Oncology core computational pathology toolkit

STAPLER (Shared TCR And Peptide Language bidirectional Encoder Representations from transformers) is a language model that uses a joint TCRab-peptide input to predict TCRab-peptide specificity.

PyTorch Lightning + Hydra. A very user-friendly template for ML experimentation. ⚡🔥⚡

Hydra is a framework for elegantly configuring complex applications

Deep learning framework for MRI reconstruction