Instructions to use patdev/NitroGen-RTX2060-ONNX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- TensorRT
How to use patdev/NitroGen-RTX2060-ONNX with TensorRT:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
| $ErrorActionPreference = "Stop" | |
| $Root = Split-Path -Parent $PSScriptRoot | |
| Set-Location $Root | |
| if (-not (Test-Path ".venv")) { py -3.12 -m venv .venv } | |
| $Py = Join-Path $Root ".venv\Scripts\python.exe" | |
| & $Py -m pip install --upgrade pip | |
| # Keep ORT on CUDA 12.x. ORT >=1.27 defaults to CUDA 13. | |
| & $Py -m pip install "onnxruntime-gpu[cuda,cudnn]>=1.24,<1.27" torch huggingface_hub numpy pyzmq | |
| if (-not (Test-Path ".vendor\NitroGen")) { | |
| New-Item -ItemType Directory -Force ".vendor" | Out-Null | |
| git clone https://github.com/MineDojo/NitroGen.git .vendor/NitroGen | |
| git -C .vendor/NitroGen checkout 32608444660950ffda95e1e57c79632ad65bea10 | |
| } | |
| & $Py -m pip install -e .vendor/NitroGen | |
| Write-Host "`nReady. Benchmark:" -ForegroundColor Green | |
| Write-Host ".\.venv\Scripts\python.exe scripts\benchmark_dit.py" | |
| Write-Host "Gameplay server (fast profile):" | |
| Write-Host ".\.venv\Scripts\python.exe scripts\serve_onnx.py --steps 4" | |