{"adoption": {"forks": 925, "observed_at": "2026-08-28T04:09:53.194458+00:00", "stars": 7006}, "canonical_url": "https://ross.abutalabs.com/products/turboquant_plus", "card": {"archived": false, "artifact_type": "library", "description": null, "domain": ["large-language-models", "deep-learning", "machine-learning", "performance"], "enriched": true, "function": ["llm-inference", "machine-learning", "benchmarking", "gpu-computing"], "health_score": 76, "homepage": null, "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["TheTom/turboquant_plus"], "name": "TheTom/turboquant_plus", "platform": ["python", "windows", "cross-platform"], "pushed_at": "2026-07-20T20:08:52+00:00", "repo": "TheTom/turboquant_plus", "stars": 7006, "tags": ["kv-cache-compression", "quantization", "polarquant", "walsh-hadamard-transform", "inference-optimization", "research-code", "memory-optimization", "gpu", "macos", "linux"], "topics": [], "urls": [], "use_cases": ["compress kv cache for long-context llm inference", "run 100b model on limited memory via cache quantization", "benchmark kv cache quantization methods", "reduce gpu memory usage for transformer inference", "research extreme kv cache compression", "speed up llm decode at long context"], "what_it_is": "TurboQuant+ is a Python reference implementation of the TurboQuant KV cache compression method (ICLR 2026), using PolarQuant codebooks and Walsh-Hadamard rotation to compress transformer KV caches 3.8-6.4x. It serves as the research home with benchmarks and validation results, with stable pieces upstreamed into engines like vLLM and llama.cpp.", "when_to_avoid": ["you just want production KV compression in a datacenter engine - use the merged vLLM flag instead", "you need a turnkey inference server - this is a research library, not an inference engine", "you need non-transformer model compression"], "when_to_choose": ["you need the full PolarQuant codec or asymmetric K/V policies not yet upstreamed", "you want the reference implementation and benchmark data for research", "you want to run very large models at long context on consumer hardware like a MacBook"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/turboquant_plus", "repo": "TheTom/turboquant_plus", "role": "main", "score": 56}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:09:53.194458+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T17:40:44.702760+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cfd46ee1f2f77013541bbeaa04f71724411caf04bc0f037a2bd1474ba13b78ee", "fetched_at": "2026-08-28T04:09:53.194458+00:00", "kind": "readme", "missing": false, "url": "https://github.com/TheTom/turboquant_plus"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:09:53.194458+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T17:40:44.702760+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cfd46ee1f2f77013541bbeaa04f71724411caf04bc0f037a2bd1474ba13b78ee", "fetched_at": "2026-08-28T04:09:53.194458+00:00", "kind": "readme", "missing": false, "url": "https://github.com/TheTom/turboquant_plus"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T17:40:44.702760+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cfd46ee1f2f77013541bbeaa04f71724411caf04bc0f037a2bd1474ba13b78ee", "fetched_at": "2026-08-28T04:09:53.194458+00:00", "kind": "readme", "missing": false, "url": "https://github.com/TheTom/turboquant_plus"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:09:53.194458+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:09:53.194458+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:09:53.194458+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T17:40:44.702760+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cfd46ee1f2f77013541bbeaa04f71724411caf04bc0f037a2bd1474ba13b78ee", "fetched_at": "2026-08-28T04:09:53.194458+00:00", "kind": "readme", "missing": false, "url": "https://github.com/TheTom/turboquant_plus"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:09:53.194458+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:09:53.194458+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T17:40:44.702760+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cfd46ee1f2f77013541bbeaa04f71724411caf04bc0f037a2bd1474ba13b78ee", "fetched_at": "2026-08-28T04:09:53.194458+00:00", "kind": "readme", "missing": false, "url": "https://github.com/TheTom/turboquant_plus"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:09:53.194458+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:09:53.194458+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:09:53.194458+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T17:40:44.702760+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cfd46ee1f2f77013541bbeaa04f71724411caf04bc0f037a2bd1474ba13b78ee", "fetched_at": "2026-08-28T04:09:53.194458+00:00", "kind": "readme", "missing": false, "url": "https://github.com/TheTom/turboquant_plus"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:09:53.194458+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:09:53.194458+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T17:40:44.702760+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cfd46ee1f2f77013541bbeaa04f71724411caf04bc0f037a2bd1474ba13b78ee", "fetched_at": "2026-08-28T04:09:53.194458+00:00", "kind": "readme", "missing": false, "url": "https://github.com/TheTom/turboquant_plus"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T17:40:44.702760+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cfd46ee1f2f77013541bbeaa04f71724411caf04bc0f037a2bd1474ba13b78ee", "fetched_at": "2026-08-28T04:09:53.194458+00:00", "kind": "readme", "missing": false, "url": "https://github.com/TheTom/turboquant_plus"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T17:40:44.702760+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cfd46ee1f2f77013541bbeaa04f71724411caf04bc0f037a2bd1474ba13b78ee", "fetched_at": "2026-08-28T04:09:53.194458+00:00", "kind": "readme", "missing": false, "url": "https://github.com/TheTom/turboquant_plus"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T17:40:44.702760+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cfd46ee1f2f77013541bbeaa04f71724411caf04bc0f037a2bd1474ba13b78ee", "fetched_at": "2026-08-28T04:09:53.194458+00:00", "kind": "readme", "missing": false, "url": "https://github.com/TheTom/turboquant_plus"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 93, "longevity": 11, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_releases", "young"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 162, "days_push": 44, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 56, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}