{"adoption": {"forks": 80, "observed_at": "2026-08-28T04:04:03.139573+00:00", "stars": 1226}, "canonical_url": "https://ross.abutalabs.com/products/minference", "card": {"archived": false, "artifact_type": "library", "description": "[NeurIPS'24 Spotlight, ICLR'25, ICML'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention, which reduces inference latency by up to 10x for pre-filling on an A100 while maintaining accuracy.", "domain": ["large-language-models", "deep-learning", "gpu-computing", "performance"], "enriched": true, "function": ["llm-inference", "gpu-computing", "machine-learning"], "health_score": 79, "homepage": "https://aka.ms/MInference", "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["microsoft/MInference"], "name": "microsoft/MInference", "platform": ["python"], "pushed_at": "2026-04-08T08:04:38+00:00", "repo": "microsoft/MInference", "stars": 1226, "tags": ["sparse-attention", "long-context", "prefill-acceleration", "vllm", "sglang", "transformers", "gpu", "linux"], "topics": [], "urls": [], "use_cases": ["speed up prefill for long-context LLM inference", "process 1M token prompts faster on a single GPU", "accelerate LLaMA or Qwen long-context models", "integrate sparse attention kernels into vLLM or SGLang", "reduce inference latency for 128K+ context windows"], "what_it_is": "MInference is a Microsoft library that accelerates long-context LLM inference using dynamic sparse attention, reducing pre-fill latency by up to 10x on an A100 while maintaining accuracy. It integrates with Hugging Face Transformers, vLLM, and SGLang and supports million-token contexts.", "when_to_avoid": ["your prompts are short and prefill is not a bottleneck", "you need exact dense attention semantics without approximation", "you don't have access to NVIDIA GPUs"], "when_to_choose": ["you serve long-context LLMs and prefill latency is a bottleneck", "you need million-token prompt processing on limited GPU hardware", "you use vLLM, SGLang, or Transformers and want drop-in sparse attention speedups"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/minference", "repo": "microsoft/MInference", "role": "main", "score": 49}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:04:03.139573+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T06:15:20.257452+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "51a8a39ab3bbdd70a370c8da4ec0f37502edc0f901157a0606706ad5eb5fb721", "fetched_at": "2026-08-28T04:04:03.139573+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/MInference"}, {"content_hash": "760dbfa9a899e33d8f28d0cb573ab5c78a877420b85a961873aac2d2a6afda3f", "fetched_at": "2026-08-29T12:23:28.920706+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/minference/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:04:03.139573+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T06:15:20.257452+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "51a8a39ab3bbdd70a370c8da4ec0f37502edc0f901157a0606706ad5eb5fb721", "fetched_at": "2026-08-28T04:04:03.139573+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/MInference"}, {"content_hash": "760dbfa9a899e33d8f28d0cb573ab5c78a877420b85a961873aac2d2a6afda3f", "fetched_at": "2026-08-29T12:23:28.920706+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/minference/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T06:15:20.257452+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "51a8a39ab3bbdd70a370c8da4ec0f37502edc0f901157a0606706ad5eb5fb721", "fetched_at": "2026-08-28T04:04:03.139573+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/MInference"}, {"content_hash": "760dbfa9a899e33d8f28d0cb573ab5c78a877420b85a961873aac2d2a6afda3f", "fetched_at": "2026-08-29T12:23:28.920706+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/minference/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:04:03.139573+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:04:03.139573+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:04:03.139573+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T06:15:20.257452+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "51a8a39ab3bbdd70a370c8da4ec0f37502edc0f901157a0606706ad5eb5fb721", "fetched_at": "2026-08-28T04:04:03.139573+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/MInference"}, {"content_hash": "760dbfa9a899e33d8f28d0cb573ab5c78a877420b85a961873aac2d2a6afda3f", "fetched_at": "2026-08-29T12:23:28.920706+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/minference/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:04:03.139573+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:04:03.139573+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T06:15:20.257452+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "51a8a39ab3bbdd70a370c8da4ec0f37502edc0f901157a0606706ad5eb5fb721", "fetched_at": "2026-08-28T04:04:03.139573+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/MInference"}, {"content_hash": "760dbfa9a899e33d8f28d0cb573ab5c78a877420b85a961873aac2d2a6afda3f", "fetched_at": "2026-08-29T12:23:28.920706+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/minference/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:04:03.139573+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:04:03.139573+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:04:03.139573+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T06:15:20.257452+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "51a8a39ab3bbdd70a370c8da4ec0f37502edc0f901157a0606706ad5eb5fb721", "fetched_at": "2026-08-28T04:04:03.139573+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/MInference"}, {"content_hash": "760dbfa9a899e33d8f28d0cb573ab5c78a877420b85a961873aac2d2a6afda3f", "fetched_at": "2026-08-29T12:23:28.920706+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/minference/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:04:03.139573+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:04:03.139573+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T06:15:20.257452+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "51a8a39ab3bbdd70a370c8da4ec0f37502edc0f901157a0606706ad5eb5fb721", "fetched_at": "2026-08-28T04:04:03.139573+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/MInference"}, {"content_hash": "760dbfa9a899e33d8f28d0cb573ab5c78a877420b85a961873aac2d2a6afda3f", "fetched_at": "2026-08-29T12:23:28.920706+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/minference/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T06:15:20.257452+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "51a8a39ab3bbdd70a370c8da4ec0f37502edc0f901157a0606706ad5eb5fb721", "fetched_at": "2026-08-28T04:04:03.139573+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/MInference"}, {"content_hash": "760dbfa9a899e33d8f28d0cb573ab5c78a877420b85a961873aac2d2a6afda3f", "fetched_at": "2026-08-29T12:23:28.920706+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/minference/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T06:15:20.257452+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "51a8a39ab3bbdd70a370c8da4ec0f37502edc0f901157a0606706ad5eb5fb721", "fetched_at": "2026-08-28T04:04:03.139573+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/MInference"}, {"content_hash": "760dbfa9a899e33d8f28d0cb573ab5c78a877420b85a961873aac2d2a6afda3f", "fetched_at": "2026-08-29T12:23:28.920706+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/minference/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T06:15:20.257452+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "51a8a39ab3bbdd70a370c8da4ec0f37502edc0f901157a0606706ad5eb5fb721", "fetched_at": "2026-08-28T04:04:03.139573+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/MInference"}, {"content_hash": "760dbfa9a899e33d8f28d0cb573ab5c78a877420b85a961873aac2d2a6afda3f", "fetched_at": "2026-08-29T12:23:28.920706+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/minference/json"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 76, "longevity": 59, "rhythm": 8}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 833, "days_push": 147, "days_rel": 442, "gap_med": null, "n_releases_24m": 1}, "score": 49, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}