{"version":"1.0","workflow_uuid":"e08ad222-37db-11f1-9bc6-00163e2b0d79","workflow_title":"Text Generation Inference (TGI) — Hugging Face Production LLM Server","install_contract":{"version":"1.0","installReady":false,"title":"Text Generation Inference (TGI) — Hugging Face Production LLM Server","summary":"TGI is Hugging Face's production-grade LLM inference server. It powers HF Inference Endpoints with continuous batching, tensor parallelism, quantization, and OpenAI-compatible APIs — handling thousands of requests per second.","assetType":"Scripts","pageUrl":"https://tokrepo.com/en/workflows/e08ad222-37db-11f1-9bc6-00163e2b0d79","sourceUrl":"http://127.0.0.1:8080/v1/chat/completions","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"]}}