Releases: NVIDIA/modulus-sym
Releases · NVIDIA/modulus-sym
v1.8.0
v1.7.0
Modulus Symbolic general release v1.7.0
Added
- AMP for derivatives.
- DALI based dataloader for Geometry module.
- Generalized PDE residual computing utility.
- Support for spatial gradients calculations using finite difference, meshless finite
difference, spectral and least squares methods. - Add docs for SDF and relevant features for geometry module.
Dependencies
- Upgrade Sympy and Scikit-Learn versions.
Security
- Upgrade notebook, opencv-python and setuptools versions to fix CVEs GHSA-9q39-rmj3-p4r2,
GHSA-qr4w-53vh-m672, and GHSA-cx63-2mw6-8hw5 respectively.
v1.6.0
Modulus Symbolic general release v1.6.0
Added
- Added inference notebook for Turbulence Super-resolution example.
Changed
- Warp based backed for STL geometry handling
Dependencies
- Update
timm
dependency - Update minimum python version to 3.10
v1.5.0
Modulus Symbolic general release v1.5.0
Added
- Added reservoir examples using GenAI and CCUS workflows.
Security
- Update OpenCV and Pillow versions to fix security
v1.4.0
Modulus Symbolic general release v1.4.0
Fixed
- Fix bug for
ConvFullyConnectedArch
. - Updating
Activation.SILU
test to conform with updated nvFuser kernel generation.
v1.3.0
Modulus Symbolic general release v1.3.0
Added
- Added instructions for docker build on ARM architecture.
- Added domain decomposition examples using X-PINN and FB-PINN style.
Changed
- Integrated the network architecture layers into Modulus-Core.
Fixed
- Fixed Gradient Aggregation bug.
Security
- Upgrade Pillow and Sympy to their latest versions.
Dependencies
- Updated base PyTorch container to 23.10 and Optix version to 7.3.0
v1.2.0
Modulus Symbolic general release v1.2.0
Added
- Example for reservoir modeling using PINO and FNO
v1.1.0
Modulus Symbolic general release v1.1.0
Added
- Added a CHANGELOG.md
Removed
- Accompanying licenses (will provide in the Modulus docker image).
Fixed
- Arch
from_config
bug for literal params. - Fixed fused SiLU activation test.
- Update
np.bool
tonp.bool_
. - Added a workaround fix for the CUDA graphs error in multi-node runs
Dependencies
- Updated the base container to latest PyTorch base container which is based on torch 2.0
- Container now supports CUDA 12, Python 3.10
- Updated symengine to >=0.10.0 and vtk to >=9.2.6
v1.0.0
Modulus symbolic general release v1.0.0
(Initial OSS release)