JAX-CFD
JAX-CFD implements incompressible Navier-Stokes solvers in JAX, making the whole time-stepping loop differentiable and JIT-compilable on accelerators.
Use cases: Hybrid neural-CFD models where a learned correction is trained through the solver; gradient-based closure modeling; turbulence model discovery.
Tags: JAXDifferentiable PhysicsCFDGoogleHybrid Modeling
Related entries
- JAX-Fluids · Fully auto-differentiable CFD solver on JAX (CPU/GPU/TPU) for end-to-end differe
- Accelerating Dropless MoE Training in JAX with NVIDIA Transformer Engine · NVIDIA Transformer Engine introduces JAX-optimized kernels for Mixture of Expert
- OpenFOAM · The de facto open-source CFD solver covering incompressible/compressible flow, h
- SU2 · Open-source CFD and adjoint solver with built-in aerodynamic shape optimization,
- DeepXDE v1.15.0 · DeepXDE v1.15.0 released with L-LAAF activation function support for JAX backend