{"version":"1.0","workflow_uuid":"735f5a27-07d6-47ac-8377-e29be76a9452","workflow_title":"MLC-LLM — Universal LLM Deployment Engine","install_contract":{"version":"1.0","installReady":false,"title":"MLC-LLM — Universal LLM Deployment Engine","summary":"Deploy any LLM on any hardware — phones, browsers, GPUs, CPUs. Compiles models for native performance on iOS, Android, WebGPU, CUDA, Metal, and Vulkan. 22K+ stars.","assetType":"Scripts","pageUrl":"https://tokrepo.com/en/workflows/mlc-llm-universal-llm-deployment-engine-735f5a27","sourceUrl":"https://webllm.mlc.ai","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"]}}