Dev
GitHub repos gaining traction - what high-signal users are starring and what's climbing the board, captured daily and enriched from GitHub. Raw material for spotting new tech and patterns worth building on.
3,195
repos tracked
105
surfaced this week
193
created < 30d
Python
top language
34 repos
-
Scribed notes for the [IFT6169] Deep Learning Theory course at UdeM
-
TabICLv2: An open tabular foundation model
-
Tensors and Dynamic neural networks in Python with strong GPU acceleration
-
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
-
Implement a reasoning LLM in PyTorch from scratch, step by step
-
Open Machine Learning Compiler Framework
-
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
-
OPAL: a reactive optimizer. A coding agent rewrites the optimizer while your model trains.
-
An open source implementation of CLIP.
-
The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more
-
Fast, flexible, elastically deterministic data loading for foundation model training
-
The official CLI and Python client for the Hugging Face Hub.
-
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
-
Calibrated 151M Non-Autoregressive Decision Engine beating TypeSafe Jev & Laya on LocalLLaMA/typed-decisions (77.10% acc, 0.0636 Brier, 0.0144 ECE)
-
Visualizer for neural network, deep learning and machine learning models
-
★ 6.5k dair-ai/Mathematics-for-ML🧮 A collection of resources to learn mathematics for machine learning
-
The fastai deep learning library
-
Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/
-
Nonlinear optimisation (root-finding, least squares, ...) in JAX+Equinox. https://docs.kidger.site/optimistix/
-
Numerical differential equation solvers in JAX. Autodifferentiable and GPU-capable. https://docs.kidger.site/diffrax/
-
Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
-
The AI Compute Platform for frontier teams. SkyPilot turns fragmented AI compute into one AI supercomputer, so frontier AI teams build custom intelligence faster.
-
Perform data science on data that remains in someone else's server
-
🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org
-
🏝️ OASIS: Open Agent Social Interaction Simulations with One Million Agents.
-
nnScaler: Compiling DNN models for Parallel Training
-
Democratizing Deep-Learning for Drug Discovery, Quantum Chemistry, Materials Science and Biology
-
Face recognition with deep neural networks.
-
Synthetic data curation for post-training and structured data extraction
-
[CVPR 2026 Highlight] A Frame is Worth One Token: Efficient Generative World Modeling with Delta Tokens
-
TensorZero is an open-source LLMOps platform that unifies an LLM gateway, observability, evaluation, optimization, and experimentation.
-
Pytorch implementation of preconditioned stochastic gradient descent (Kron and affine preconditioner, low-rank approximation preconditioner and more)
-
We write your reusable computer vision tools. 💜