{"adoption": {"forks": 195, "observed_at": "2026-08-28T04:05:29.993142+00:00", "stars": 1739}, "canonical_url": "https://ross.abutalabs.com/products/turboquant", "card": {"archived": false, "artifact_type": "library", "description": "TurboQuant: Near-optimal KV cache quantization for LLM inference (3-bit keys, 2-bit values) with Triton kernels + vLLM integration", "domain": ["large-language-models", "machine-learning", "gpu-computing", "performance"], "enriched": true, "function": ["llm-inference", "gpu-computing", "caching", "machine-learning"], "health_score": 65, "homepage": null, "language": "Python", "license": "GPL-3.0", "license_family": "copyleft", "maturity": "active", "member_repos": ["0xSero/turboquant"], "name": "0xSero/turboquant", "platform": ["python"], "pushed_at": "2026-03-27T22:30:40+00:00", "repo": "0xSero/turboquant", "stars": 1739, "tags": ["kv-cache-quantization", "vllm", "triton-kernels", "inference-optimization", "moe", "gpu", "linux", "docker"], "topics": [], "urls": [], "use_cases": ["reduce KV cache memory usage during LLM inference", "double the max context/token capacity of a vLLM deployment", "serve long-context LLMs on limited GPU VRAM", "quantize KV cache to 3-bit keys and 2-bit values", "speed up prefill and decode throughput for large context windows", "run MoE models with mixed full and linear attention layers more efficiently"], "what_it_is": "TurboQuant is a Python library implementing near-optimal KV cache quantization for LLM inference, compressing keys to 3-bit and values to 2-bit using Triton kernels. It integrates with vLLM and supports dense and MoE architectures on NVIDIA GPUs.", "when_to_avoid": ["your model uses only linear-attention layers, which TurboQuant cannot compress", "you need a non-vLLM inference engine without integration support", "you require permissive licensing since the project is GPL-3.0", "you need CPU-only or non-CUDA inference"], "when_to_choose": ["you use vLLM and need to fit longer contexts or more concurrent requests in GPU memory", "you want drop-in KV cache compression with minimal quality loss", "you run inference on NVIDIA GPUs (RTX 3090/5090 class) with dense or MoE models"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/turboquant", "repo": "0xSero/turboquant", "role": "main", "score": 48}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:05:29.993142+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T03:30:12.544914+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c86933af7ae90339443626eec267082fa472b0ee0e5fa369e99f0489f1dcbad2", "fetched_at": "2026-08-28T04:05:29.993142+00:00", "kind": "readme", "missing": false, "url": "https://github.com/0xSero/turboquant"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:05:29.993142+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T03:30:12.544914+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c86933af7ae90339443626eec267082fa472b0ee0e5fa369e99f0489f1dcbad2", "fetched_at": "2026-08-28T04:05:29.993142+00:00", "kind": "readme", "missing": false, "url": "https://github.com/0xSero/turboquant"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T03:30:12.544914+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c86933af7ae90339443626eec267082fa472b0ee0e5fa369e99f0489f1dcbad2", "fetched_at": "2026-08-28T04:05:29.993142+00:00", "kind": "readme", "missing": false, "url": "https://github.com/0xSero/turboquant"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:05:29.993142+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:05:29.993142+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:05:29.993142+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T03:30:12.544914+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c86933af7ae90339443626eec267082fa472b0ee0e5fa369e99f0489f1dcbad2", "fetched_at": "2026-08-28T04:05:29.993142+00:00", "kind": "readme", "missing": false, "url": "https://github.com/0xSero/turboquant"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:05:29.993142+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:05:29.993142+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T03:30:12.544914+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c86933af7ae90339443626eec267082fa472b0ee0e5fa369e99f0489f1dcbad2", "fetched_at": "2026-08-28T04:05:29.993142+00:00", "kind": "readme", "missing": false, "url": "https://github.com/0xSero/turboquant"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:05:29.993142+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:05:29.993142+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:05:29.993142+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T03:30:12.544914+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c86933af7ae90339443626eec267082fa472b0ee0e5fa369e99f0489f1dcbad2", "fetched_at": "2026-08-28T04:05:29.993142+00:00", "kind": "readme", "missing": false, "url": "https://github.com/0xSero/turboquant"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:05:29.993142+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:05:29.993142+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T03:30:12.544914+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c86933af7ae90339443626eec267082fa472b0ee0e5fa369e99f0489f1dcbad2", "fetched_at": "2026-08-28T04:05:29.993142+00:00", "kind": "readme", "missing": false, "url": "https://github.com/0xSero/turboquant"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T03:30:12.544914+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c86933af7ae90339443626eec267082fa472b0ee0e5fa369e99f0489f1dcbad2", "fetched_at": "2026-08-28T04:05:29.993142+00:00", "kind": "readme", "missing": false, "url": "https://github.com/0xSero/turboquant"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T03:30:12.544914+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c86933af7ae90339443626eec267082fa472b0ee0e5fa369e99f0489f1dcbad2", "fetched_at": "2026-08-28T04:05:29.993142+00:00", "kind": "readme", "missing": false, "url": "https://github.com/0xSero/turboquant"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T03:30:12.544914+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c86933af7ae90339443626eec267082fa472b0ee0e5fa369e99f0489f1dcbad2", "fetched_at": "2026-08-28T04:05:29.993142+00:00", "kind": "readme", "missing": false, "url": "https://github.com/0xSero/turboquant"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 74, "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": 161, "days_push": 159, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 48, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}