{"version":"1.0","workflow_uuid":"92079e30-57ad-11f1-9bc6-00163e2b0d79","workflow_title":"TensorRT-LLM — High-Performance LLM Inference on NVIDIA GPUs","install_contract":{"version":"1.0","installReady":false,"title":"TensorRT-LLM — High-Performance LLM Inference on NVIDIA GPUs","summary":"NVIDIA's open-source library for optimizing and deploying large language models with state-of-the-art inference performance on NVIDIA hardware.","assetType":"Configs","pageUrl":"https://tokrepo.com/en/workflows/asset-92079e30","sourceUrl":"https://github.com/NVIDIA/TensorRT-LLM","intendedFor":[],"firstActions":[],"agentFirstSteps":[],"targetPaths":[],"verification":[],"startingPoints":[],"example":"","successOutcome":"","boundaries":[],"askUserIf":["the current workspace stack cannot be matched to a safe upstream template","the target path is not the project root, or an existing file should be merged instead of overwritten"]}}