Mircea Mironenco

Train the smallest LM you can that fits in 16MB. Best model wins!

Small vllm-style inference engine.

A small LLM post-training & fine-tuning library designed primarily to allow for simplified custom component integration.

A PyTorch native platform for training generative AI models

Implementation of Bayesian Recurrent Neural Networks by Fortunato et. al

A Python-embedded DSL that makes it easy to write fast, scalable ML kernels with minimal boilerplate.

Efficient implementations of state-of-the-art linear attention models in Pytorch and Triton

A PyTorch repo for data loading and utilities to be shared by the PyTorch domain libraries.

PyTorch-native post-training at scale

TorchStore is a distributed KV Cache for Tensors.

PyTorch native finetuning library

Official implementation of Lie Group Decompositions for Equivariant Neural Networks (ICLR 2024)

CLI interfaces & config objects, from types

No description provided.

No description provided.

Create powerful Hydra applications without the yaml files and boilerplate code.

Development repository for the Triton language and compiler

Tensorflow implementation of autoencoder architectures.

Machine Learning 2 Course 2017 - MSc Artificial Intelligence @ UvA

Equivariant Steerable CNNs Library for Pytorch

Translation of http://e-maxx.ru into English

Tensors and Dynamic neural networks in Python with strong GPU acceleration

EPI Judge - Preview Release

Computations involving Lie groups and harmonic analysis

Group Equivariant Convolutional Neural Networks

University of Amsterdam Computer Vision 1 Programming Assignments

Examining Cooperation in Visual Dialog Models

tf.layers style implementation of stochastic neural network models.

Tensorflow implementation of GAN architectures.

Code for the paper "VAE with a VampPrior", J.M. Tomczak & M. Welling