Data

Tools

Indexes

Applications

Experiments

Open Source Science

Recent Releases of https://github.com/openmm/nnpops

https://github.com/openmm/nnpops - NNPOps 0.6

What's Changed

  • Add Self-Hosted AWS GPU Runner by @mikemhenry in https://github.com/openmm/NNPOps/pull/100
  • Particle Mesh Ewald by @peastman in https://github.com/openmm/NNPOps/pull/103
  • Fix CMake not adding some tests by @RaulPPelaez in https://github.com/openmm/NNPOps/pull/104
  • Make some tests use deterministic torch algorithms by @RaulPPelaez in https://github.com/openmm/NNPOps/pull/108

New Contributors

  • @mikemhenry made their first contribution in https://github.com/openmm/NNPOps/pull/100

Full Changelog: https://github.com/openmm/NNPOps/compare/v0.5...v0.6

- C++
Published by raimis almost 3 years ago

https://github.com/openmm/nnpops - NNPOps 0.5

What's Changed

  • Update CI versions by @raimis in https://github.com/openmm/NNPOps/pull/88
  • Additions to .gitignore by @RaulPPelaez in https://github.com/openmm/NNPOps/pull/90
  • Fix neighbourlist gradient calculation on CPU by @sef43 in https://github.com/openmm/NNPOps/pull/91
  • Move all torch.ops.load calls to the __init__.py scripts by @RaulPPelaez in https://github.com/openmm/NNPOps/pull/89
  • Fix incorrect decorator in NNPOps by @RaulPPelaez in https://github.com/openmm/NNPOps/pull/93
  • Fix CMake not updating tests correctly after first run by @RaulPPelaez in https://github.com/openmm/NNPOps/pull/97
  • Add error checking to CUDA version of getNeighborPairs by @RaulPPelaez in https://github.com/openmm/NNPOps/pull/80
  • Support for pytorch 2.0 by @RaulPPelaez in https://github.com/openmm/NNPOps/pull/94

Full Changelog: https://github.com/openmm/NNPOps/compare/v0.4...v0.5

- C++
Published by raimis about 3 years ago

https://github.com/openmm/nnpops - NNPOps 0.4

This release fixes a bug in the periodic boundary conditions in NNPOps.SymmetryFunctions.TorchANISymmetryFunctions and improves the build system.

What's Changed

  • Improve the build system to use findpackage(Python) instead of findpackage(PythonLibs) by @RaulPPelaez in https://github.com/openmm/NNPOps/pull/81
  • Fix a bug in the periodic boundary conditions in ANI SymmetryFunctions by @sef43 in https://github.com/openmm/NNPOps/pull/83

New Contributors

  • @RaulPPelaez made their first contribution in https://github.com/openmm/NNPOps/pull/81
  • @sef43 made their first contribution in https://github.com/openmm/NNPOps/pull/83

Full Changelog: https://github.com/openmm/NNPOps/compare/v0.3...v0.4

- C++
Published by raimis over 3 years ago

https://github.com/openmm/nnpops - NNPOps 0.3

This release brings the nearest neighbor operation NNPOps.neighbors.getNeighborPairs and a few bug fixes.

What's Changed

  • Update README by @raimis in https://github.com/openmm/NNPOps/pull/52
  • Fix and improve CI by @raimis in https://github.com/openmm/NNPOps/pull/56
  • Nearest neighbor operation by @raimis in https://github.com/openmm/NNPOps/pull/58
  • getNeighborPairs compute the displacement vector by @raimis in https://github.com/openmm/NNPOps/pull/61
  • Use Mamba for CI by @raimis in https://github.com/openmm/NNPOps/pull/64
  • Refactor the common code by @raimis in https://github.com/openmm/NNPOps/pull/65
  • Fix the selection of the activation function in CFConv by @raimis in https://github.com/openmm/NNPOps/pull/67
  • Workaround for pytorch bug by @peastman in https://github.com/openmm/NNPOps/pull/71
  • Align SpeciesConverter return type with TorchANI version by @scal444 in https://github.com/openmm/NNPOps/pull/74
  • Update the CI versions by @raimis in https://github.com/openmm/NNPOps/pull/75
  • getNeighborPairs() supports periodic boundary conditions by @peastman in https://github.com/openmm/NNPOps/pull/70

New Contributors

  • @scal444 made their first contribution in https://github.com/openmm/NNPOps/pull/74

Full Changelog: https://github.com/openmm/NNPOps/compare/v0.2...v0.3

- C++
Published by raimis over 3 years ago

https://github.com/openmm/nnpops - NNPOps 0.2

This release brings a full support of TorchANI via NNPOps.OptimizeTorchANI. Additionally, the PyTorch wrappers for the continuous-filter convolution (CFConv) operations have been implemented, which will be used to accelerate TorchMD-Net.

What's Changed

  • Optimization to SchNet by @peastman in https://github.com/openmm/NNPOps/pull/42
  • Fix the execution of ANISymmetryFunctions on a non-default CUDA stream by @raimis in https://github.com/openmm/NNPOps/pull/37
  • Move the TorchANI imports from the top level by @raimis in https://github.com/openmm/NNPOps/pull/45
  • Optimize EnergyShifter of TorchANI by @raimis in https://github.com/openmm/NNPOps/pull/38
  • Optimize SpeciesConverter of TorchANI by @raimis in https://github.com/openmm/NNPOps/pull/39
  • Optimize TorchANI by @raimis in https://github.com/openmm/NNPOps/pull/41
  • Enable CPU-only builds by @raimis in https://github.com/openmm/NNPOps/pull/48
  • Improve the wrapper of ANISymmetryFunctions by @raimis in https://github.com/openmm/NNPOps/pull/47
  • PyTorch wrapper for SchNet operations by @raimis in https://github.com/openmm/NNPOps/pull/40
  • Refactor the CUDA error check by @raimis in https://github.com/openmm/NNPOps/pull/49

Full Changelog: https://github.com/openmm/NNPOps/compare/v0.1...v0.2

- C++
Published by raimis over 4 years ago

https://github.com/openmm/nnpops - NNPOps 0.1

What's Changed

  • Update to TorchANI 2.2.2 by @raimis in https://github.com/openmm/NNPOps/pull/35

Full Changelog: https://github.com/openmm/NNPOps/compare/v0.0...v0.1

- C++
Published by raimis over 4 years ago

https://github.com/openmm/nnpops - NNPOps 0.0

The first official release! It provides a minimal functionality to accelerate the ANI models from TorchANI.

What's Changed

  • CUDA implementation of ANISymmetryFunctions by @peastman in https://github.com/openmm/NNPOps/pull/4
  • Optimizations to CudaANISymmetryFunctions by @peastman in https://github.com/openmm/NNPOps/pull/7
  • Further optimizations to CudaANISymmetryFunctions by @peastman in https://github.com/openmm/NNPOps/pull/8
  • Fix a memory leak in CudaANISymmetryFunctions by @raimis in https://github.com/openmm/NNPOps/pull/9
  • Added README files and benchmark code by @peastman in https://github.com/openmm/NNPOps/pull/12
  • PyTorch wrapper by @raimis in https://github.com/openmm/NNPOps/pull/5
  • mdtraj xyz unit by @yueyericardo in https://github.com/openmm/NNPOps/pull/17
  • CFConv layer for SchNet by @peastman in https://github.com/openmm/NNPOps/pull/18
  • Added option to use tanh activation by @peastman in https://github.com/openmm/NNPOps/pull/23
  • A better PyTorch wrapper by @raimis in https://github.com/openmm/NNPOps/pull/19
  • Reorganize repo by @raimis in https://github.com/openmm/NNPOps/pull/33
  • Batched NNs for TorchANI by @raimis in https://github.com/openmm/NNPOps/pull/13
  • CI for NNPOps by @raimis in https://github.com/openmm/NNPOps/pull/34

New Contributors

  • @peastman made their first contribution in https://github.com/openmm/NNPOps/pull/4
  • @raimis made their first contribution in https://github.com/openmm/NNPOps/pull/9
  • @yueyericardo made their first contribution in https://github.com/openmm/NNPOps/pull/17

- C++
Published by raimis over 4 years ago