{"adoption": {"forks": 196, "observed_at": "2026-08-28T04:03:59.779259+00:00", "stars": 1209}, "canonical_url": "https://ross.abutalabs.com/products/r-kv", "card": {"archived": false, "artifact_type": "library", "description": "[Neurips 2025] R-KV: Redundancy-aware KV Cache Compression for Reasoning Models", "domain": ["large-language-models", "machine-learning", "performance", "gpu-computing"], "enriched": true, "function": ["llm-inference", "caching", "machine-learning", "benchmarking"], "health_score": 76, "homepage": "https://zefan-cai.github.io/R-KV.page/", "language": "Python", "license": null, "license_family": "other", "maturity": "active", "member_repos": ["Zefan-Cai/R-KV"], "name": "Zefan-Cai/R-KV", "platform": ["python"], "pushed_at": "2026-07-20T04:54:05+00:00", "repo": "Zefan-Cai/R-KV", "stars": 1209, "tags": ["kv-cache-compression", "reasoning-models", "vllm", "sglang", "chain-of-thought", "training-free", "inference-optimization", "research-paper", "gpu", "linux", "docker"], "topics": ["kvcache", "llm", "reasoning-models"], "urls": [], "use_cases": ["compress kv cache during llm chain-of-thought inference", "reduce gpu memory for reasoning model serving", "increase llm serving throughput under memory constraints", "run long self-reflection reasoning without cache blowup", "speed up rl rollout inference for reasoning models", "benchmark kv cache compression on gsm8k"], "what_it_is": "R-KV is a training-free, redundancy-aware KV cache compression method for reasoning LLMs, discarding repetitive tokens on-the-fly during decoding to retain ~full accuracy with only ~10% of the cache. It ships as a plug-and-play wrapper plus performance-hardened ports for vLLM and SGLang serving engines.", "when_to_avoid": ["compressing long prompts rather than long generated traces", "you need a permissively licensed dependency (no license file)", "non-reasoning workloads with short outputs where cache pressure is low", "you need a turnkey product rather than a research codebase"], "when_to_choose": ["serving reasoning models (CoT/self-reflection) whose long outputs bloat the KV cache", "you need near-lossless accuracy at 10-16% cache budget", "you use vLLM or SGLang and want a patch-based integration", "you want a training-free, plug-and-play compression wrapper"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/r-kv", "repo": "Zefan-Cai/R-KV", "role": "main", "score": 60}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:03:59.779259+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T06:18:34.091815+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5641c5e027eb641a7c4e631da08401d8d41bffa9f8bfe27486eaf5ebe67ff27c", "fetched_at": "2026-08-28T04:03:59.779259+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Zefan-Cai/R-KV"}, {"content_hash": "9f427c41aea9c44ecb472787f25ebb146d2f7d641c0b61fae03b5bfb5125e61a", "fetched_at": "2026-08-29T12:26:27.002857+00:00", "kind": "homepage", "missing": false, "url": "https://zefan-cai.github.io/R-KV.page/"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:03:59.779259+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T06:18:34.091815+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5641c5e027eb641a7c4e631da08401d8d41bffa9f8bfe27486eaf5ebe67ff27c", "fetched_at": "2026-08-28T04:03:59.779259+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Zefan-Cai/R-KV"}, {"content_hash": "9f427c41aea9c44ecb472787f25ebb146d2f7d641c0b61fae03b5bfb5125e61a", "fetched_at": "2026-08-29T12:26:27.002857+00:00", "kind": "homepage", "missing": false, "url": "https://zefan-cai.github.io/R-KV.page/"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T06:18:34.091815+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5641c5e027eb641a7c4e631da08401d8d41bffa9f8bfe27486eaf5ebe67ff27c", "fetched_at": "2026-08-28T04:03:59.779259+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Zefan-Cai/R-KV"}, {"content_hash": "9f427c41aea9c44ecb472787f25ebb146d2f7d641c0b61fae03b5bfb5125e61a", "fetched_at": "2026-08-29T12:26:27.002857+00:00", "kind": "homepage", "missing": false, "url": "https://zefan-cai.github.io/R-KV.page/"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:03:59.779259+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:03:59.779259+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:03:59.779259+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T06:18:34.091815+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5641c5e027eb641a7c4e631da08401d8d41bffa9f8bfe27486eaf5ebe67ff27c", "fetched_at": "2026-08-28T04:03:59.779259+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Zefan-Cai/R-KV"}, {"content_hash": "9f427c41aea9c44ecb472787f25ebb146d2f7d641c0b61fae03b5bfb5125e61a", "fetched_at": "2026-08-29T12:26:27.002857+00:00", "kind": "homepage", "missing": false, "url": "https://zefan-cai.github.io/R-KV.page/"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:03:59.779259+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:03:59.779259+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T06:18:34.091815+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5641c5e027eb641a7c4e631da08401d8d41bffa9f8bfe27486eaf5ebe67ff27c", "fetched_at": "2026-08-28T04:03:59.779259+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Zefan-Cai/R-KV"}, {"content_hash": "9f427c41aea9c44ecb472787f25ebb146d2f7d641c0b61fae03b5bfb5125e61a", "fetched_at": "2026-08-29T12:26:27.002857+00:00", "kind": "homepage", "missing": false, "url": "https://zefan-cai.github.io/R-KV.page/"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:03:59.779259+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:03:59.779259+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:03:59.779259+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T06:18:34.091815+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5641c5e027eb641a7c4e631da08401d8d41bffa9f8bfe27486eaf5ebe67ff27c", "fetched_at": "2026-08-28T04:03:59.779259+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Zefan-Cai/R-KV"}, {"content_hash": "9f427c41aea9c44ecb472787f25ebb146d2f7d641c0b61fae03b5bfb5125e61a", "fetched_at": "2026-08-29T12:26:27.002857+00:00", "kind": "homepage", "missing": false, "url": "https://zefan-cai.github.io/R-KV.page/"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:03:59.779259+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:03:59.779259+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T06:18:34.091815+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5641c5e027eb641a7c4e631da08401d8d41bffa9f8bfe27486eaf5ebe67ff27c", "fetched_at": "2026-08-28T04:03:59.779259+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Zefan-Cai/R-KV"}, {"content_hash": "9f427c41aea9c44ecb472787f25ebb146d2f7d641c0b61fae03b5bfb5125e61a", "fetched_at": "2026-08-29T12:26:27.002857+00:00", "kind": "homepage", "missing": false, "url": "https://zefan-cai.github.io/R-KV.page/"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T06:18:34.091815+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5641c5e027eb641a7c4e631da08401d8d41bffa9f8bfe27486eaf5ebe67ff27c", "fetched_at": "2026-08-28T04:03:59.779259+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Zefan-Cai/R-KV"}, {"content_hash": "9f427c41aea9c44ecb472787f25ebb146d2f7d641c0b61fae03b5bfb5125e61a", "fetched_at": "2026-08-29T12:26:27.002857+00:00", "kind": "homepage", "missing": false, "url": "https://zefan-cai.github.io/R-KV.page/"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T06:18:34.091815+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5641c5e027eb641a7c4e631da08401d8d41bffa9f8bfe27486eaf5ebe67ff27c", "fetched_at": "2026-08-28T04:03:59.779259+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Zefan-Cai/R-KV"}, {"content_hash": "9f427c41aea9c44ecb472787f25ebb146d2f7d641c0b61fae03b5bfb5125e61a", "fetched_at": "2026-08-29T12:26:27.002857+00:00", "kind": "homepage", "missing": false, "url": "https://zefan-cai.github.io/R-KV.page/"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T06:18:34.091815+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5641c5e027eb641a7c4e631da08401d8d41bffa9f8bfe27486eaf5ebe67ff27c", "fetched_at": "2026-08-28T04:03:59.779259+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Zefan-Cai/R-KV"}, {"content_hash": "9f427c41aea9c44ecb472787f25ebb146d2f7d641c0b61fae03b5bfb5125e61a", "fetched_at": "2026-08-29T12:26:27.002857+00:00", "kind": "homepage", "missing": false, "url": "https://zefan-cai.github.io/R-KV.page/"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 93, "longevity": 32, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_releases", "no_license"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 461, "days_push": 44, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 60, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}