NVIDIA NIM for GenMol# GenMol Overview Introduction Applications NIM Features References Release Notes Release 1.0.0 Summary Limitation Getting Started Prerequisites NGC (NVIDIA GPU Cloud) Account NGC CLI Tool Model-Specific Requirements Launch GenMol NIM Run Inference in Linux Shell Run Inference with Python Molecular Sequence as Input/Output Stopping the Container Serving Models from Local Assets Air Gap Deployment (offline cache route) Air Gap Deployment (local model directory route) Configure NIM View NIM Container Information Pull the container image Docker NGC Runtime Parameters for the Container Run Multiple Instances on the Same Host Model Checkpoint Caching Logging NIM Endpoints Molecular Generation Input Parameters Outputs Example Readiness Check Input Parameters Outputs Example List Models and Versions Input Parameters Outputs Example API Reference Input Parameters Outputs Support Matrix Models Supported Hardware GPU Minimum GPU Memory Disk Space CUDA Compute Capability Supported Software NVIDIA Driver and Prerequisite Utilities List Available Model Profiles Example Download Model Profiles to NIM Cache Example Create Model Store Example Check NIM Cache Example Set Cache Environment Variables Example Benchmarks Performance Accuracy
