Tensors and Dynamic neural networks in Python with strong GPU acceleration

Official inference framework for 1-bit LLMs

You like pytorch? You like micrograd? You love tinygrad! ❤️

A playbook for systematically maximizing the performance of deep learning models.

LLM training in simple, raw C/CUDA

An open-source RAG-based tool for chatting with your documents.

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

Kolmogorov Arnold Networks

Convert Machine Learning Code Between Frameworks

High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.

[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer

Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation" (CVPR'25 Spotlight).

ModelScope: bring the notion of Model-as-a-Service to life.

The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that sho…

Minimal web UI for ChatGPT.

Sharp Monocular View Synthesis in Less Than a Second

Python code for "Probabilistic Machine learning" book by Kevin Murphy

Time series Timeseries Deep Learning Machine Learning Python Pytorch fastai | State-of-the-art Deep Learning library for Time Series and Sequences in Pytorch / fastai

A GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep learning training and inference applications.

Curated list of data science interview questions and answers

Nightly release of ControlNet 1.1

Easily train or fine-tune SOTA computer vision models with one open source training library. The home of Yolo-NAS.

Text recognition (optical character recognition) with deep learning methods, ICCV 2019

Deformable DETR: Deformable Transformers for End-to-End Object Detection.

T2I-Adapter

🧠💬 Articles I wrote about machine learning, archived from MachineCurve.com.

[NeurIPS 2024] Unique3D: High-Quality and Efficient 3D Mesh Generation from a Single Image

Efficient vision foundation models for high-resolution generation and perception.

[ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-to-end metrics across language, image, and video models.