{"adoption": {"forks": 1340, "observed_at": "2026-08-28T04:09:40.979285+00:00", "stars": 6252}, "canonical_url": "https://ross.abutalabs.com/products/flashinfer", "card": {"archived": false, "artifact_type": "library", "description": "FlashInfer: Kernel Library for LLM Serving", "domain": ["large-language-models", "deep-learning", "gpu-computing", "machine-learning", "developer-tools"], "enriched": true, "function": ["llm-inference", "gpu-computing", "machine-learning", "deep-learning", "benchmarking"], "health_score": 100, "homepage": "https://flashinfer.ai", "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["flashinfer-ai/flashinfer"], "name": "flashinfer-ai/flashinfer", "platform": ["python"], "pushed_at": "2026-08-26T23:28:33+00:00", "repo": "flashinfer-ai/flashinfer", "stars": 6252, "tags": ["cuda-kernels", "attention", "mixture-of-experts", "kv-cache", "fp8", "fp4", "jit-compilation", "vllm", "inference-serving", "pytorch", "gpu", "linux", "cuda"], "topics": ["gpu", "large-large-models", "cuda", "pytorch", "llm-inference", "jit", "attention", "nvidia", "distributed-inference", "moe"], "urls": [], "use_cases": ["speed up LLM inference serving on NVIDIA GPUs", "efficient attention kernels with paged KV-cache for dynamic batching", "fused mixture-of-experts kernels for MoE models", "FP8 and FP4 quantized attention and GEMM", "accelerate decode and prefill in vLLM or custom serving engines", "shared-prefix cascade attention for memory-efficient batching", "MLA attention kernels for DeepSeek models"], "what_it_is": "FlashInfer is a GPU kernel library and kernel generator for LLM inference, providing unified APIs for attention, GEMM, and MoE operations with multiple backends (FlashAttention-2/3, cuDNN, CUTLASS, TensorRT-LLM). It supports paged KV-cache, FP8/FP4 low-precision compute, CUDA Graphs, and GPUs from Turing through Blackwell.", "when_to_avoid": ["you're running inference on CPUs or non-NVIDIA accelerators without supported backends", "you just need a simple high-level inference API rather than kernel-level control", "your workload is small-scale where kernel optimization overhead isn't worth it"], "when_to_choose": ["you need state-of-the-art GPU kernel performance for LLM serving", "you're building or tuning an inference engine like vLLM or SGLang", "you need low-precision (FP8/FP4) attention, GEMM, or MoE on modern NVIDIA GPUs", "you want backend flexibility with automatic hardware-aware kernel selection"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/flashinfer", "repo": "flashinfer-ai/flashinfer", "role": "main", "score": 90}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:09:40.979285+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T17:46:36.285294+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "16122ce128b4f4a742ce4bad892572eb0ab8ba9939b3f5abdcfaf6c49665e6eb", "fetched_at": "2026-08-28T04:09:40.979285+00:00", "kind": "readme", "missing": false, "url": "https://github.com/flashinfer-ai/flashinfer"}, {"content_hash": "47c1526e3085f833e7411b1f0b9d34f5e5680ae3fff11935da5132da491807b3", "fetched_at": "2026-08-29T08:43:23.021918+00:00", "kind": "homepage", "missing": false, "url": "https://flashinfer.ai"}, {"content_hash": "01c21b9b7af58eac1e528350ad6176950594358ecfcfb01bf4acb138c82c65f1", "fetched_at": "2026-08-29T08:43:23.030955+00:00", "kind": "site_page", "missing": false, "url": "https://docs.flashinfer.ai/"}, {"content_hash": "2ef5495fa6e3b266e9a59c36cf8d1f5086d4aa7a0a53634899164fcd12032fcf", "fetched_at": "2026-08-29T08:43:23.034325+00:00", "kind": "site_page", "missing": false, "url": "https://flashinfer.ai/releases"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:09:40.979285+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T17:46:36.285294+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "16122ce128b4f4a742ce4bad892572eb0ab8ba9939b3f5abdcfaf6c49665e6eb", "fetched_at": "2026-08-28T04:09:40.979285+00:00", "kind": "readme", "missing": false, "url": "https://github.com/flashinfer-ai/flashinfer"}, {"content_hash": "47c1526e3085f833e7411b1f0b9d34f5e5680ae3fff11935da5132da491807b3", "fetched_at": "2026-08-29T08:43:23.021918+00:00", "kind": "homepage", "missing": false, "url": "https://flashinfer.ai"}, {"content_hash": "01c21b9b7af58eac1e528350ad6176950594358ecfcfb01bf4acb138c82c65f1", "fetched_at": "2026-08-29T08:43:23.030955+00:00", "kind": "site_page", "missing": false, "url": "https://docs.flashinfer.ai/"}, {"content_hash": "2ef5495fa6e3b266e9a59c36cf8d1f5086d4aa7a0a53634899164fcd12032fcf", "fetched_at": "2026-08-29T08:43:23.034325+00:00", "kind": "site_page", "missing": false, "url": "https://flashinfer.ai/releases"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T17:46:36.285294+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "16122ce128b4f4a742ce4bad892572eb0ab8ba9939b3f5abdcfaf6c49665e6eb", "fetched_at": "2026-08-28T04:09:40.979285+00:00", "kind": "readme", "missing": false, "url": "https://github.com/flashinfer-ai/flashinfer"}, {"content_hash": "47c1526e3085f833e7411b1f0b9d34f5e5680ae3fff11935da5132da491807b3", "fetched_at": "2026-08-29T08:43:23.021918+00:00", "kind": "homepage", "missing": false, "url": "https://flashinfer.ai"}, {"content_hash": "01c21b9b7af58eac1e528350ad6176950594358ecfcfb01bf4acb138c82c65f1", "fetched_at": "2026-08-29T08:43:23.030955+00:00", "kind": "site_page", "missing": false, "url": "https://docs.flashinfer.ai/"}, {"content_hash": "2ef5495fa6e3b266e9a59c36cf8d1f5086d4aa7a0a53634899164fcd12032fcf", "fetched_at": "2026-08-29T08:43:23.034325+00:00", "kind": "site_page", "missing": false, "url": "https://flashinfer.ai/releases"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:09:40.979285+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:09:40.979285+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:09:40.979285+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T17:46:36.285294+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "16122ce128b4f4a742ce4bad892572eb0ab8ba9939b3f5abdcfaf6c49665e6eb", "fetched_at": "2026-08-28T04:09:40.979285+00:00", "kind": "readme", "missing": false, "url": "https://github.com/flashinfer-ai/flashinfer"}, {"content_hash": "47c1526e3085f833e7411b1f0b9d34f5e5680ae3fff11935da5132da491807b3", "fetched_at": "2026-08-29T08:43:23.021918+00:00", "kind": "homepage", "missing": false, "url": "https://flashinfer.ai"}, {"content_hash": "01c21b9b7af58eac1e528350ad6176950594358ecfcfb01bf4acb138c82c65f1", "fetched_at": "2026-08-29T08:43:23.030955+00:00", "kind": "site_page", "missing": false, "url": "https://docs.flashinfer.ai/"}, {"content_hash": "2ef5495fa6e3b266e9a59c36cf8d1f5086d4aa7a0a53634899164fcd12032fcf", "fetched_at": "2026-08-29T08:43:23.034325+00:00", "kind": "site_page", "missing": false, "url": "https://flashinfer.ai/releases"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:09:40.979285+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:09:40.979285+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T17:46:36.285294+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "16122ce128b4f4a742ce4bad892572eb0ab8ba9939b3f5abdcfaf6c49665e6eb", "fetched_at": "2026-08-28T04:09:40.979285+00:00", "kind": "readme", "missing": false, "url": "https://github.com/flashinfer-ai/flashinfer"}, {"content_hash": "47c1526e3085f833e7411b1f0b9d34f5e5680ae3fff11935da5132da491807b3", "fetched_at": "2026-08-29T08:43:23.021918+00:00", "kind": "homepage", "missing": false, "url": "https://flashinfer.ai"}, {"content_hash": "01c21b9b7af58eac1e528350ad6176950594358ecfcfb01bf4acb138c82c65f1", "fetched_at": "2026-08-29T08:43:23.030955+00:00", "kind": "site_page", "missing": false, "url": "https://docs.flashinfer.ai/"}, {"content_hash": "2ef5495fa6e3b266e9a59c36cf8d1f5086d4aa7a0a53634899164fcd12032fcf", "fetched_at": "2026-08-29T08:43:23.034325+00:00", "kind": "site_page", "missing": false, "url": "https://flashinfer.ai/releases"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:09:40.979285+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:09:40.979285+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:09:40.979285+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T17:46:36.285294+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "16122ce128b4f4a742ce4bad892572eb0ab8ba9939b3f5abdcfaf6c49665e6eb", "fetched_at": "2026-08-28T04:09:40.979285+00:00", "kind": "readme", "missing": false, "url": "https://github.com/flashinfer-ai/flashinfer"}, {"content_hash": "47c1526e3085f833e7411b1f0b9d34f5e5680ae3fff11935da5132da491807b3", "fetched_at": "2026-08-29T08:43:23.021918+00:00", "kind": "homepage", "missing": false, "url": "https://flashinfer.ai"}, {"content_hash": "01c21b9b7af58eac1e528350ad6176950594358ecfcfb01bf4acb138c82c65f1", "fetched_at": "2026-08-29T08:43:23.030955+00:00", "kind": "site_page", "missing": false, "url": "https://docs.flashinfer.ai/"}, {"content_hash": "2ef5495fa6e3b266e9a59c36cf8d1f5086d4aa7a0a53634899164fcd12032fcf", "fetched_at": "2026-08-29T08:43:23.034325+00:00", "kind": "site_page", "missing": false, "url": "https://flashinfer.ai/releases"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:09:40.979285+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:09:40.979285+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T17:46:36.285294+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "16122ce128b4f4a742ce4bad892572eb0ab8ba9939b3f5abdcfaf6c49665e6eb", "fetched_at": "2026-08-28T04:09:40.979285+00:00", "kind": "readme", "missing": false, "url": "https://github.com/flashinfer-ai/flashinfer"}, {"content_hash": "47c1526e3085f833e7411b1f0b9d34f5e5680ae3fff11935da5132da491807b3", "fetched_at": "2026-08-29T08:43:23.021918+00:00", "kind": "homepage", "missing": false, "url": "https://flashinfer.ai"}, {"content_hash": "01c21b9b7af58eac1e528350ad6176950594358ecfcfb01bf4acb138c82c65f1", "fetched_at": "2026-08-29T08:43:23.030955+00:00", "kind": "site_page", "missing": false, "url": "https://docs.flashinfer.ai/"}, {"content_hash": "2ef5495fa6e3b266e9a59c36cf8d1f5086d4aa7a0a53634899164fcd12032fcf", "fetched_at": "2026-08-29T08:43:23.034325+00:00", "kind": "site_page", "missing": false, "url": "https://flashinfer.ai/releases"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T17:46:36.285294+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "16122ce128b4f4a742ce4bad892572eb0ab8ba9939b3f5abdcfaf6c49665e6eb", "fetched_at": "2026-08-28T04:09:40.979285+00:00", "kind": "readme", "missing": false, "url": "https://github.com/flashinfer-ai/flashinfer"}, {"content_hash": "47c1526e3085f833e7411b1f0b9d34f5e5680ae3fff11935da5132da491807b3", "fetched_at": "2026-08-29T08:43:23.021918+00:00", "kind": "homepage", "missing": false, "url": "https://flashinfer.ai"}, {"content_hash": "01c21b9b7af58eac1e528350ad6176950594358ecfcfb01bf4acb138c82c65f1", "fetched_at": "2026-08-29T08:43:23.030955+00:00", "kind": "site_page", "missing": false, "url": "https://docs.flashinfer.ai/"}, {"content_hash": "2ef5495fa6e3b266e9a59c36cf8d1f5086d4aa7a0a53634899164fcd12032fcf", "fetched_at": "2026-08-29T08:43:23.034325+00:00", "kind": "site_page", "missing": false, "url": "https://flashinfer.ai/releases"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T17:46:36.285294+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "16122ce128b4f4a742ce4bad892572eb0ab8ba9939b3f5abdcfaf6c49665e6eb", "fetched_at": "2026-08-28T04:09:40.979285+00:00", "kind": "readme", "missing": false, "url": "https://github.com/flashinfer-ai/flashinfer"}, {"content_hash": "47c1526e3085f833e7411b1f0b9d34f5e5680ae3fff11935da5132da491807b3", "fetched_at": "2026-08-29T08:43:23.021918+00:00", "kind": "homepage", "missing": false, "url": "https://flashinfer.ai"}, {"content_hash": "01c21b9b7af58eac1e528350ad6176950594358ecfcfb01bf4acb138c82c65f1", "fetched_at": "2026-08-29T08:43:23.030955+00:00", "kind": "site_page", "missing": false, "url": "https://docs.flashinfer.ai/"}, {"content_hash": "2ef5495fa6e3b266e9a59c36cf8d1f5086d4aa7a0a53634899164fcd12032fcf", "fetched_at": "2026-08-29T08:43:23.034325+00:00", "kind": "site_page", "missing": false, "url": "https://flashinfer.ai/releases"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T17:46:36.285294+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "16122ce128b4f4a742ce4bad892572eb0ab8ba9939b3f5abdcfaf6c49665e6eb", "fetched_at": "2026-08-28T04:09:40.979285+00:00", "kind": "readme", "missing": false, "url": "https://github.com/flashinfer-ai/flashinfer"}, {"content_hash": "47c1526e3085f833e7411b1f0b9d34f5e5680ae3fff11935da5132da491807b3", "fetched_at": "2026-08-29T08:43:23.021918+00:00", "kind": "homepage", "missing": false, "url": "https://flashinfer.ai"}, {"content_hash": "01c21b9b7af58eac1e528350ad6176950594358ecfcfb01bf4acb138c82c65f1", "fetched_at": "2026-08-29T08:43:23.030955+00:00", "kind": "site_page", "missing": false, "url": "https://docs.flashinfer.ai/"}, {"content_hash": "2ef5495fa6e3b266e9a59c36cf8d1f5086d4aa7a0a53634899164fcd12032fcf", "fetched_at": "2026-08-29T08:43:23.034325+00:00", "kind": "site_page", "missing": false, "url": "https://flashinfer.ai/releases"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "longevity": 81, "rhythm": 85}, "computed_at": "2026-09-03T02:39:23.370411+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 1139, "days_push": 7, "days_rel": 22, "gap_med": 5, "n_releases_24m": 62}, "score": 90, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}