{"adoption": {"forks": 179, "observed_at": "2026-08-28T04:04:33.106115+00:00", "stars": 1375}, "canonical_url": "https://ross.abutalabs.com/products/kvcache-factory", "card": {"archived": false, "artifact_type": "library", "description": "Unified KV Cache Compression Methods for Auto-Regressive Models", "domain": ["large-language-models", "deep-learning", "machine-learning"], "enriched": true, "function": ["llm-inference", "machine-learning", "benchmarking"], "health_score": 78, "homepage": null, "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["Zefan-Cai/KVCache-Factory"], "name": "Zefan-Cai/KVCache-Factory", "platform": ["python"], "pushed_at": "2026-08-13T07:35:40+00:00", "repo": "Zefan-Cai/KVCache-Factory", "stars": 1375, "tags": ["kv-cache", "kv-cache-compression", "long-context", "inference-optimization", "pyramidkv", "quantization", "attention", "gpu", "linux"], "topics": ["kv-cache", "kv-cache-compression", "llm"], "urls": [], "use_cases": ["compress kv cache for long-context llm inference", "benchmark kv cache eviction methods on longbench", "reduce gpu memory for llama or mistral inference", "compare pyramidkv vs snapkv vs h2o", "quantize kv cache with kivi or kvquant", "offload kv cache to cpu for 70b models", "evaluate needle-in-a-haystack retrieval under cache compression"], "what_it_is": "KVCache-Factory is a unified Python framework implementing many KV cache compression, retrieval, merging, and quantization methods for long-context LLM inference. It provides a single evaluation interface across methods like PyramidKV, SnapKV, H2O, Quest, MiniCache, and KIVI.", "when_to_avoid": ["you need production serving with high throughput rather than research evaluation", "your model architecture is not Llama or Mistral style", "you need broad coverage of the newest methods without checking runner support"], "when_to_choose": ["you need to experiment with or compare many KV cache compression methods under one interface", "you are running long-context inference on limited GPU memory", "you want reproducible LongBench-style evaluation of cache baselines"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/kvcache-factory", "repo": "Zefan-Cai/KVCache-Factory", "role": "main", "score": 68}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:04:33.106115+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T04:40:33.354072+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cc33c1e68a884ef738370339ba87a1b9fb41d9153a74d22ada2b289b8ef5240b", "fetched_at": "2026-08-28T04:04:33.106115+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Zefan-Cai/KVCache-Factory"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:04:33.106115+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T04:40:33.354072+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cc33c1e68a884ef738370339ba87a1b9fb41d9153a74d22ada2b289b8ef5240b", "fetched_at": "2026-08-28T04:04:33.106115+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Zefan-Cai/KVCache-Factory"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T04:40:33.354072+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cc33c1e68a884ef738370339ba87a1b9fb41d9153a74d22ada2b289b8ef5240b", "fetched_at": "2026-08-28T04:04:33.106115+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Zefan-Cai/KVCache-Factory"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:04:33.106115+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:04:33.106115+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:04:33.106115+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T04:40:33.354072+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cc33c1e68a884ef738370339ba87a1b9fb41d9153a74d22ada2b289b8ef5240b", "fetched_at": "2026-08-28T04:04:33.106115+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Zefan-Cai/KVCache-Factory"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:04:33.106115+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:04:33.106115+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T04:40:33.354072+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cc33c1e68a884ef738370339ba87a1b9fb41d9153a74d22ada2b289b8ef5240b", "fetched_at": "2026-08-28T04:04:33.106115+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Zefan-Cai/KVCache-Factory"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:04:33.106115+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:04:33.106115+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:04:33.106115+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T04:40:33.354072+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cc33c1e68a884ef738370339ba87a1b9fb41d9153a74d22ada2b289b8ef5240b", "fetched_at": "2026-08-28T04:04:33.106115+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Zefan-Cai/KVCache-Factory"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:04:33.106115+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:04:33.106115+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T04:40:33.354072+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cc33c1e68a884ef738370339ba87a1b9fb41d9153a74d22ada2b289b8ef5240b", "fetched_at": "2026-08-28T04:04:33.106115+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Zefan-Cai/KVCache-Factory"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T04:40:33.354072+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cc33c1e68a884ef738370339ba87a1b9fb41d9153a74d22ada2b289b8ef5240b", "fetched_at": "2026-08-28T04:04:33.106115+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Zefan-Cai/KVCache-Factory"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T04:40:33.354072+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cc33c1e68a884ef738370339ba87a1b9fb41d9153a74d22ada2b289b8ef5240b", "fetched_at": "2026-08-28T04:04:33.106115+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Zefan-Cai/KVCache-Factory"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T04:40:33.354072+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cc33c1e68a884ef738370339ba87a1b9fb41d9153a74d22ada2b289b8ef5240b", "fetched_at": "2026-08-28T04:04:33.106115+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Zefan-Cai/KVCache-Factory"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 97, "longevity": 58, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 819, "days_push": 20, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 68, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}