an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficie…

A PyTorch library for implementing flow matching algorithms, featuring continuous and discrete flow matching implementations. It includes practical examples for both text and image modalities.

Annotations of the interesting ML papers I read

General purpose unsupervised sentence representations

A collection of resources and papers on Diffusion Models

AMD ROCm™ Software - GitHub Home

Modern C++ Programming Course (C++03/11/14/17/20/23/26)

Pruna is a model optimization framework built for developers, enabling you to deliver faster, more efficient models with minimal overhead.

A Easy-to-understand TensorOp Matmul Tutorial

A one-stop repository for large language model (LLM) unlearning. Supports TOFU, MUSE and is an easily extensible framework for new datasets, evaluations, methods, and other benchmarks.

PyTorch video decoding

Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution (https://arxiv.org/abs/2310.16834)

A project page template for academic papers. Demo at https://eliahuhorwitz.github.io/Academic-project-page-template/

Test-time-training on nearest neighbors for large language models

ControlArena is a suite of realistic settings, mimicking complex deployment environments, for running control evaluations. This is an alpha release; we welcome feedback.

Lecture notes and cheatsheets for Master's in Computer Science at ETH Zurich

University of Tübingen M.Sc. Machine Learning Projects

Code accompanying the paper "Generalized Interpolating Discrete Diffusion"

Make websites accessible for AI agents

🦉 OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation

No fortress, purely open ground. OpenManus is Coming.

This repository is the official project page of the course AI in the Sciences and Engineering, ETH Zurich.

Retrieval and Retrieval-augmented LLMs

FlagGems is an operator library for large language models implemented in Triton Language.

Repository of the journal club "Diffusion Models and Generative Modeling"

Notebooks for fine tuning pali gemma

A lightweight data processing framework built on DuckDB and 3FS.

Google Summer of Code resources.