Download Latest Version v2.0.0 source code.zip (154.4 MB)
Email in envelope

Get an email when there's a new version of NVIDIA PhysicsNeMo

Home / v1.1.0
Name Modified Size InfoDownloads / Week
Parent folder
README.md 2025-06-10 2.1 kB
0
v1.1.0 source code.tar.gz 2025-06-10 121.6 MB
0
v1.1.0 source code.zip 2025-06-10 122.7 MB
0
Totals: 3 Items   244.3 MB 0

PhysicsNeMo (Core) General Release v1.1.0

Added

  • Added ReGen score-based data assimilation example
  • General purpose patching API for patch-based diffusion
  • New positional embedding selection strategy for CorrDiff SongUNet models
  • Added Multi-Storage Client to allow checkpointing to/from Object Storage

Changed

  • Simplified CorrDiff config files, updated default values
  • Refactored CorrDiff losses and samplers to use the patching API
  • Support for non-square images and patches in patch-based diffusion
  • ERA5 download example updated to use current file format convention and restricts global statistics computation to the training set
  • Support for training custom StormCast models and various other improvements for StormCast
  • Updated CorrDiff training code to support multiple patch iterations to amortize regression cost and usage of torch.compile
  • Refactored physicsnemo/models/diffusion/layers.py to optimize data type casting workflow, avoiding unnecessary casting under autocast mode
  • Refactored Conv2d to enable fusion of conv2d with bias addition
  • Refactored GroupNorm, UNetBlock, SongUNet, SongUNetPosEmbd to support usage of Apex GroupNorm, fusion of activation with GroupNorm, and AMP workflow.
  • Updated SongUNetPosEmbd to avoid unnecessary HtoD Memcpy of pos_embd
  • Updated from_checkpoint to accommodate conversion between Apex optimized ckp and non-optimized ckp
  • Refactored CorrDiff NVTX annotation workflow to be configurable
  • Refactored ResidualLoss to support patch-accumlating training for amortizing regression costs
  • Explicit handling of Warp device for ball query and sdf
  • Merged SongUNetPosLtEmb with SongUNetPosEmb, add support for batch>1
  • Add lead time embedding support for positional_embedding_selector. Enable
    arbitrary positioning of probabilistic variables
  • Enable lead time aware regression without CE loss
  • Bumped minimum PyTorch version from 2.0.0 to 2.4.0, to minimize support surface for physicsnemo.distributed functionality.

Dependencies

  • Made nvidia.dali an optional dependency
Source: README.md, updated 2025-06-10