torchebm

Simulation-free, GPU-first generative modeling in PyTorch: composable primitives for scalable, stable training of modern energy-based models, diffusion, flow matching, and Schrödinger bridges.

Installation

In a virtualenv (see these instructions if you need to create one):

pip3 install torchebm

Dependencies

Releases

Version Released Bookworm
Python 3.11
Trixie
Python 3.13
Files
0.8.7 2026-09-07    
0.8.6 2026-09-02    
0.8.5 2026-09-01    
0.8.4 2026-09-01    
0.8.3 2026-09-01    
0.8.2 2026-08-30    
0.8.0 2026-08-28    
0.7.5 2026-07-16    
0.7.1 2026-07-13    
0.6.0 2026-05-31    
0.5.8 2026-02-17    
0.5.7 2026-02-12    
0.5.6 2026-02-12    
0.5.4 2026-02-11    
0.5.1 2025-12-29    
0.5.0 2025-12-23  
0.4.0 2025-10-10    
0.3.17 2025-08-22    
0.3.7 2025-05-02    
0.3.5 2025-04-27    
0.3.4 2025-04-24    
0.3.0 2025-04-18    
0.2.6 2025-04-13    
0.2.4 2025-04-11    
0.1.0 2024-10-05    

Issues with this package?

Page last updated 2026-09-07 04:18:45 UTC