Source

nvidia/nvalchemi-toolkit

12 skills · 24 combined installs

Skills from this source

#
Skill
Source
8W Activity
Installs
1
nvalchemi-dynamics-hooks >- How to use and write dynamics hooks — callbacks that observe or modify batch state at specific points during each …
nvidia/nvalchemi-toolkit
3
2
nvalchemi-data-storage How to write, read, compose, and load atomic data using nvalchemi's composable Zarr-backed storage pipeline (Writer, …
nvidia/nvalchemi-toolkit
2
3
nvalchemi-data-structures >- How to use AtomicData and Batch, the core graph-based data structures for representing atomic systems and batching…
nvidia/nvalchemi-toolkit
2
4
nvalchemi-dynamics-api >- How to configure and run dynamics simulations, compose multi-stage pipelines (FusedStage, DistributedPipeline), us…
nvidia/nvalchemi-toolkit
2
5
nvalchemi-dynamics-implementation >- How to implement a dynamics integrator by subclassing BaseDynamics and overriding pre_update() and post_update() m…
nvidia/nvalchemi-toolkit
2
6
nvalchemi-fine-tuning >- How to fine-tune nvalchemi-compatible models with FineTuningStrategy, pretrained checkpoint initialization, module…
nvidia/nvalchemi-toolkit
2
7
nvalchemi-loss-api >- How to use built-in loss functions and implement custom losses using the BaseLossFunction template-method pattern …
nvidia/nvalchemi-toolkit
2
8
nvalchemi-model-wrapping How to wrap an arbitrary MLIP (Machine Learning Interatomic Potential) using the BaseModelMixin interface to standard…
nvidia/nvalchemi-toolkit
2
9
nvalchemi-reporting >- How to add observability to nvalchemi dynamics and training workflows using ReportingOrchestrator, RichReporter, T…
nvidia/nvalchemi-toolkit
2
10
nvalchemi-training-api >- How to configure nvalchemi training workflows with TrainingStrategy, custom training functions, standalone or comp…
nvidia/nvalchemi-toolkit
2
11
nvalchemi-zarr-perf >- Performance tuning for nvalchemi's Zarr-backed Reader, Dataset, and DataLoader pipeline. Use when configuring Atom…
nvidia/nvalchemi-toolkit
2
12
nvalchemi-distributed How to run domain-decomposed (multi-GPU) MLIP simulations with DomainParallel — choose between the halo and graph-par…
nvidia/nvalchemi-toolkit
1