{"version":"1.0","workflow_uuid":"f758afa2-8fb4-4ba6-9b3d-738559d2a0b0","workflow_title":"SGLang — Fast LLM Serving with RadixAttention","install_contract":{"version":"1.0","installReady":false,"title":"SGLang — Fast LLM Serving with RadixAttention","summary":"SGLang is a high-performance serving framework for LLMs and multimodal models. 25.3K+ GitHub stars. RadixAttention prefix caching, speculative decoding, structured outputs. NVIDIA/AMD/Intel/TPU. Apach","assetType":"Scripts","pageUrl":"https://tokrepo.com/en/workflows/sglang-fast-llm-serving-radixattention-f758afa2","sourceUrl":"http://localhost:30000/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"]}}