{"version":"1.0","workflow_uuid":"d8dc39ce-57ad-11f1-9bc6-00163e2b0d79","workflow_title":"FlashInfer — Kernel Library for LLM Serving","install_contract":{"version":"1.0","installReady":false,"title":"FlashInfer — Kernel Library for LLM Serving","summary":"High-performance CUDA kernel library providing optimized attention, decoding, and prefill operations for LLM inference engines like vLLM and SGLang.","assetType":"Configs","pageUrl":"https://tokrepo.com/en/workflows/asset-d8dc39ce","sourceUrl":"https://flashinfer.ai/whl/cu124/torch2.4/","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"]}}