arpastrana / jax_fdm
Auto-differentiable and hardware-accelerated force density method
Why this job: works in the areas we cover, but does not say which job it does
What it does
- Legendary form-finding solver.
- Derivatives, JIT compilation, and parallelization.
- Autotune those force densities, loads, and supports.
- A rich bank of goals, constraints, and loss functions.
- Structural simulations as another layer in a neural network.
Get started
pip install jax-fdm- Maintenance
- Active
- Last commit yesterday
- Stars
- 121
- On GitHub
- Licence
- MIT
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v0.14.1
- Released 2 months ago
- Built with
- Python
- 96% of the code
Is it looked after?
- Contributors
- 1
- Last 90 days
- Issues
- 100% closed
- 0 still open
- Pull requests
- 26 merged
- 0 waiting
- Releases
- 32
- 7 in the last year
- Contributing guide (opens in new tab)
- No security policy
- Code of conduct (opens in new tab)
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| google-deepmind / optax | 2,366 | today | Apache-2.0 | No downloads |
| JuliaDecisionFocusedLearning / ImplicitDifferentiation.jl | 147 | 6 days ago | MIT | No downloads |
More: languages, topics and project record
Languages
- Python 96%
- Jupyter Notebook 4%
Topics
- architecture
- automatic-differentiation
- form-finding
- jax
- structural-design
- machine-learning
- optimization
- differentiable-mechanics
Project record
- JobOther AI tools
- StatusListed
- Commits848
- Forks7
- Watching1
- Stars in 28 days+1
- CreatedSep 8, 2022
- First seen by usNov 7, 2026
- CheckedNov 12, 2026