RUN SOLVERAI PREDICTION

Runs SolverAI inference using a trained model checkpoint on new simulations. Takes a completed SolverAI training simulation (with best_val_model.pt) and prediction simulation IDs, submits a GPU job that produces d3plot and binout output files identical to a normal LS-DYNA solve.

When to use

Tagged: solverai, gpu, prediction, inference, deep_learning, hpc, d3plot, binout.

Inputs

Label	ID	Type	Default	Required	Description
Prediction Job Name	job_name	text	—	✓	Name for the SolverAI prediction simulation record.
Training Simulation	training_simulation	remote_lookup	—	✓	Completed SolverAI training simulation that contains best_val_model.pt checkpoint.
Prediction Simulations	prediction_simulations	remote_lookup	—	✓	Simulation IDs to run prediction on. Each must have d3plot files in its vault.
Config File	config_file	file	—		Override predict configuration (.yaml). Defaults are generated automatically.
HPC Config	hpc_config	remote_lookup	—	✓	Saved HPC configuration with SolverAI solver type and GPU queue.
Run Name	run_name	text	—		Name of the training run subfolder (e.g. default_train, MGN_v2, MGN_Disp_ps). For training: sets the subfolder name. For prediction: must match the training run name to find the correct checkpoint. If empty, auto-detected from the first available checkpoint.

Outputs

Label	ID	Type	Description
Simulation Id	simulation_id	integer	ID of the SolverAI prediction simulation with d3plot and binout outputs.
Hpcjob Id	hpcjob_id	integer	ID of the HPC job record tracking the GPU prediction run.
Prediction Count	prediction_count	integer	Number of simulations being predicted.
Training Simulation Id	training_simulation_id	integer	ID of the training simulation whose model was used.

Disciplines

• platform.hpc_config
• platform.job_submission
• solverai.prediction

---

Auto-generated from platform schema. Worker id: job_predict_solverai_by_config. Schema hash: 10a80895a6e9. Hand-curated docs in workerexamples/ override this page when present.