Deep Learning Frameworks
Core deep learning training and inference frameworks — PyTorch, TensorFlow, JAX, and similar stacks.
213 projects
See methodology for ranking rules; order uses public GitHub metrics within this scenario.
| Rank | Project | Stars | Forks | Updated | License |
|---|---|---|---|---|---|
| 61 |
SynapseML
Simple and Distributed Machine Learning Python Library porting ML algorithms for Spark |
5.2K | 868 | 08/28/26 | MIT |
| 62 |
tch-rs
Rust bindings for the C++ api of PyTorch. |
5.5K | 452 | 08/23/26 | Apache-2.0 |
| 63 |
oneflow
OneFlow is a deep learning framework designed to be user-friendly, scalable and efficient. |
9.4K | 1.0K | 12/04/25 | Apache-2.0 |
| 64 |
nccl
Optimized primitives for collective multi-GPU communication |
5.0K | 1.4K | 08/29/26 | Other |
| 65 |
Flux.jl
Relax! Flux is the ML library that doesn't make you tensor |
4.7K | 625 | 08/16/26 | Other |
| 66 |
djl
An Engine-Agnostic Deep Learning Framework in Java |
4.8K | 760 | 08/29/26 | Apache-2.0 |
| 67 |
xtuner
A Next-Generation Training Engine Built for Ultra-Large MoE Models |
5.2K | 447 | 08/28/26 | Apache-2.0 |
| 68 |
autokeras
AutoML library for deep learning |
9.3K | 1.4K | 11/25/25 | Apache-2.0 |
| 69 |
mmf
A modular framework for vision & language multimodal research from Facebook AI Research (FAIR) |
5.6K | 938 | 07/07/26 | Other |
| 70 |
EasyR1
EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL |
5.1K | 390 | 08/26/26 | Apache-2.0 |
| 71 |
kaolin
A PyTorch Library for Accelerating 3D Deep Learning Research |
5.2K | 628 | 08/24/26 | Apache-2.0 |
| 72 |
flashlight
A C++ standalone library for machine learning |
5.5K | 501 | 06/22/26 | MIT |
| 73 |
deepxde
A library for scientific machine learning and physics-informed learning |
4.4K | 990 | 08/18/26 | LGPL-2.1 |
| 74 |
rl
A modular, primitive-first, python-first PyTorch library for Reinforcement Learning. |
3.5K | 478 | 08/29/26 | MIT |
| 75 |
TransformerEngine
A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on Hopper, Ada and Blackwell GPUs, to provide better performance with lower memory utilization in both training and inference. |
3.5K | 814 | 08/29/26 | Apache-2.0 |
| 76 |
composer
Supercharge Your Model Training |
5.5K | 467 | 04/29/26 | Apache-2.0 |
| 77 |
PettingZoo
A standard API for multi-agent reinforcement learning environments, with popular reference environments and related utilities |
3.5K | 520 | 08/13/26 | MIT |
| 78 |
vector-quantize-pytorch
Vector (and Scalar) Quantization, in Pytorch |
4.0K | 337 | 08/02/26 | MIT |
| 79 |
dm-haiku
JAX-based neural network library |
3.3K | 299 | 08/25/26 | Apache-2.0 |
| 80 |
physicsnemo
Open-source deep-learning framework for building, training, and fine-tuning deep learning models using state-of-the-art Physics-ML methods |
3.2K | 766 | 08/28/26 | Apache-2.0 |