DeepXDE v1.15.0
DeepXDE is a deep learning library for solving differential equations. Version 1.15.0 adds L-LAAF activation function support for the JAX backend and fixes Apple MPS GPU support for the PyTorch backend. The release also introduces FirstDerivative callback argument improvements, PFNN subnetwork remerging capabilities, and mini batch support for PointSetOperatorBC.
Tags: PDEDeep LearningScientific ComputingPyTorchJAX
Related entries
- NeuralOperator v2.0.0 Release · NeuralOperator 2.0.0 major release introduces Codano model, improves documentati
- Accelerating Dropless MoE Training in JAX with NVIDIA Transformer Engine · NVIDIA Transformer Engine introduces JAX-optimized kernels for Mixture of Expert
- PhysicsNeMo v2.2.2 · NVIDIA PhysicsNeMo v2.2.2 release fixes documentation alignment with the PyPi pa
- JAX-Fluids · Fully auto-differentiable CFD solver on JAX (CPU/GPU/TPU) for end-to-end differe
- FEniCS/dolfinx v0.11.0.post0 Released · FEniCS/dolfinx releases a patch version that fixes a Mathjax rendering issue in