{"adoption": {"forks": 637, "observed_at": "2026-08-28T04:08:15.663534+00:00", "stars": 3726}, "canonical_url": "https://ross.abutalabs.com/products/llm-compressor", "card": {"archived": false, "artifact_type": "library", "description": "Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM", "domain": ["large-language-models", "machine-learning", "deep-learning", "gpu-computing"], "enriched": true, "function": ["machine-learning", "llm-training", "compression", "serialization"], "health_score": 100, "homepage": "https://docs.vllm.ai/projects/llm-compressor", "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["vllm-project/llm-compressor"], "name": "vllm-project/llm-compressor", "platform": ["python", "cross-platform"], "pushed_at": "2026-08-26T22:26:14+00:00", "repo": "vllm-project/llm-compressor", "stars": 3726, "tags": ["quantization", "model-optimization", "vllm", "compressed-tensors", "hugging-face", "moe", "pruning", "fp8", "int4", "linux", "gpu"], "topics": ["compression", "quantization"], "urls": [], "use_cases": ["quantize an LLM to fp8 or int4 for vLLM inference", "reduce GPU memory requirements for serving large language models", "compress a Hugging Face model into compressed-tensors format", "prune experts from a mixture-of-experts model", "speed up LLM inference with lower-precision weights"], "what_it_is": "LLM Compressor is a Python library for applying quantization and pruning algorithms to large language models, producing compressed-tensors checkpoints optimized for vLLM deployment. It integrates with Hugging Face Transformers and supports weight, activation, KV cache, and attention quantization including MoE expert pruning.", "when_to_avoid": ["you expect faster inference through plain transformers - compressed models only accelerate in vLLM or compatible servers", "you need a serving engine itself rather than a model compression tool", "you require SGLang support, which is minimally maintained"], "when_to_choose": ["you deploy models with vLLM and want smaller, faster checkpoints", "you need state-of-the-art quantization schemes like NVFP4, FP8, or arbitrary bit-widths", "you work with Hugging Face Transformers models and want a pip-installable optimization pipeline"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/llm-compressor", "repo": "vllm-project/llm-compressor", "role": "main", "score": 90}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:08:15.663534+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T18:29:15.664794+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "dfc04828c70aa6203e1ddb95f06af2a14afc215d26803b923031c6371d94d6e9", "fetched_at": "2026-08-28T04:08:15.663534+00:00", "kind": "readme", "missing": false, "url": "https://github.com/vllm-project/llm-compressor"}, {"content_hash": "af790c8b7937deeeab6d99eaa6085101e5f3871fe36b16dee87764c7aeb6f089", "fetched_at": "2026-08-29T09:23:53.532677+00:00", "kind": "homepage", "missing": false, "url": "https://docs.vllm.ai/projects/llm-compressor"}, {"content_hash": "563d18d8696d5d2e5ce52d2b0cc971d87cbfb081c45b7c9135cab0bb3cdd69e4", "fetched_at": "2026-08-29T09:23:53.535623+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/llm-compressor/en/latest/getting-started"}, {"content_hash": "325a3fd81fbe1493e038ee3cb8f05b990544fa24666e40c1cb6bda983b40376c", "fetched_at": "2026-08-29T09:23:53.537588+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/llm-compressor/en/latest/getting-started/install"}, {"content_hash": "56a03c6d3d74dc50afb213d4a5b12ab572b8c9ee0c9bb8b7738a0544e372187c", "fetched_at": "2026-08-29T09:23:53.539461+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/llm-compressor/en/latest/faq/faq"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:08:15.663534+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T18:29:15.664794+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "dfc04828c70aa6203e1ddb95f06af2a14afc215d26803b923031c6371d94d6e9", "fetched_at": "2026-08-28T04:08:15.663534+00:00", "kind": "readme", "missing": false, "url": "https://github.com/vllm-project/llm-compressor"}, {"content_hash": "af790c8b7937deeeab6d99eaa6085101e5f3871fe36b16dee87764c7aeb6f089", "fetched_at": "2026-08-29T09:23:53.532677+00:00", "kind": "homepage", "missing": false, "url": "https://docs.vllm.ai/projects/llm-compressor"}, {"content_hash": "563d18d8696d5d2e5ce52d2b0cc971d87cbfb081c45b7c9135cab0bb3cdd69e4", "fetched_at": "2026-08-29T09:23:53.535623+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/llm-compressor/en/latest/getting-started"}, {"content_hash": "325a3fd81fbe1493e038ee3cb8f05b990544fa24666e40c1cb6bda983b40376c", "fetched_at": "2026-08-29T09:23:53.537588+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/llm-compressor/en/latest/getting-started/install"}, {"content_hash": "56a03c6d3d74dc50afb213d4a5b12ab572b8c9ee0c9bb8b7738a0544e372187c", "fetched_at": "2026-08-29T09:23:53.539461+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/llm-compressor/en/latest/faq/faq"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T18:29:15.664794+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "dfc04828c70aa6203e1ddb95f06af2a14afc215d26803b923031c6371d94d6e9", "fetched_at": "2026-08-28T04:08:15.663534+00:00", "kind": "readme", "missing": false, "url": "https://github.com/vllm-project/llm-compressor"}, {"content_hash": "af790c8b7937deeeab6d99eaa6085101e5f3871fe36b16dee87764c7aeb6f089", "fetched_at": "2026-08-29T09:23:53.532677+00:00", "kind": "homepage", "missing": false, "url": "https://docs.vllm.ai/projects/llm-compressor"}, {"content_hash": "563d18d8696d5d2e5ce52d2b0cc971d87cbfb081c45b7c9135cab0bb3cdd69e4", "fetched_at": "2026-08-29T09:23:53.535623+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/llm-compressor/en/latest/getting-started"}, {"content_hash": "325a3fd81fbe1493e038ee3cb8f05b990544fa24666e40c1cb6bda983b40376c", "fetched_at": "2026-08-29T09:23:53.537588+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/llm-compressor/en/latest/getting-started/install"}, {"content_hash": "56a03c6d3d74dc50afb213d4a5b12ab572b8c9ee0c9bb8b7738a0544e372187c", "fetched_at": "2026-08-29T09:23:53.539461+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/llm-compressor/en/latest/faq/faq"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:08:15.663534+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:08:15.663534+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:08:15.663534+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T18:29:15.664794+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "dfc04828c70aa6203e1ddb95f06af2a14afc215d26803b923031c6371d94d6e9", "fetched_at": "2026-08-28T04:08:15.663534+00:00", "kind": "readme", "missing": false, "url": "https://github.com/vllm-project/llm-compressor"}, {"content_hash": "af790c8b7937deeeab6d99eaa6085101e5f3871fe36b16dee87764c7aeb6f089", "fetched_at": "2026-08-29T09:23:53.532677+00:00", "kind": "homepage", "missing": false, "url": "https://docs.vllm.ai/projects/llm-compressor"}, {"content_hash": "563d18d8696d5d2e5ce52d2b0cc971d87cbfb081c45b7c9135cab0bb3cdd69e4", "fetched_at": "2026-08-29T09:23:53.535623+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/llm-compressor/en/latest/getting-started"}, {"content_hash": "325a3fd81fbe1493e038ee3cb8f05b990544fa24666e40c1cb6bda983b40376c", "fetched_at": "2026-08-29T09:23:53.537588+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/llm-compressor/en/latest/getting-started/install"}, {"content_hash": "56a03c6d3d74dc50afb213d4a5b12ab572b8c9ee0c9bb8b7738a0544e372187c", "fetched_at": "2026-08-29T09:23:53.539461+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/llm-compressor/en/latest/faq/faq"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:08:15.663534+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:08:15.663534+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T18:29:15.664794+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "dfc04828c70aa6203e1ddb95f06af2a14afc215d26803b923031c6371d94d6e9", "fetched_at": "2026-08-28T04:08:15.663534+00:00", "kind": "readme", "missing": false, "url": "https://github.com/vllm-project/llm-compressor"}, {"content_hash": "af790c8b7937deeeab6d99eaa6085101e5f3871fe36b16dee87764c7aeb6f089", "fetched_at": "2026-08-29T09:23:53.532677+00:00", "kind": "homepage", "missing": false, "url": "https://docs.vllm.ai/projects/llm-compressor"}, {"content_hash": "563d18d8696d5d2e5ce52d2b0cc971d87cbfb081c45b7c9135cab0bb3cdd69e4", "fetched_at": "2026-08-29T09:23:53.535623+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/llm-compressor/en/latest/getting-started"}, {"content_hash": "325a3fd81fbe1493e038ee3cb8f05b990544fa24666e40c1cb6bda983b40376c", "fetched_at": "2026-08-29T09:23:53.537588+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/llm-compressor/en/latest/getting-started/install"}, {"content_hash": "56a03c6d3d74dc50afb213d4a5b12ab572b8c9ee0c9bb8b7738a0544e372187c", "fetched_at": "2026-08-29T09:23:53.539461+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/llm-compressor/en/latest/faq/faq"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:08:15.663534+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:08:15.663534+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:08:15.663534+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T18:29:15.664794+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "dfc04828c70aa6203e1ddb95f06af2a14afc215d26803b923031c6371d94d6e9", "fetched_at": "2026-08-28T04:08:15.663534+00:00", "kind": "readme", "missing": false, "url": "https://github.com/vllm-project/llm-compressor"}, {"content_hash": "af790c8b7937deeeab6d99eaa6085101e5f3871fe36b16dee87764c7aeb6f089", "fetched_at": "2026-08-29T09:23:53.532677+00:00", "kind": "homepage", "missing": false, "url": "https://docs.vllm.ai/projects/llm-compressor"}, {"content_hash": "563d18d8696d5d2e5ce52d2b0cc971d87cbfb081c45b7c9135cab0bb3cdd69e4", "fetched_at": "2026-08-29T09:23:53.535623+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/llm-compressor/en/latest/getting-started"}, {"content_hash": "325a3fd81fbe1493e038ee3cb8f05b990544fa24666e40c1cb6bda983b40376c", "fetched_at": "2026-08-29T09:23:53.537588+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/llm-compressor/en/latest/getting-started/install"}, {"content_hash": "56a03c6d3d74dc50afb213d4a5b12ab572b8c9ee0c9bb8b7738a0544e372187c", "fetched_at": "2026-08-29T09:23:53.539461+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/llm-compressor/en/latest/faq/faq"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:08:15.663534+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:08:15.663534+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T18:29:15.664794+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "dfc04828c70aa6203e1ddb95f06af2a14afc215d26803b923031c6371d94d6e9", "fetched_at": "2026-08-28T04:08:15.663534+00:00", "kind": "readme", "missing": false, "url": "https://github.com/vllm-project/llm-compressor"}, {"content_hash": "af790c8b7937deeeab6d99eaa6085101e5f3871fe36b16dee87764c7aeb6f089", "fetched_at": "2026-08-29T09:23:53.532677+00:00", "kind": "homepage", "missing": false, "url": "https://docs.vllm.ai/projects/llm-compressor"}, {"content_hash": "563d18d8696d5d2e5ce52d2b0cc971d87cbfb081c45b7c9135cab0bb3cdd69e4", "fetched_at": "2026-08-29T09:23:53.535623+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/llm-compressor/en/latest/getting-started"}, {"content_hash": "325a3fd81fbe1493e038ee3cb8f05b990544fa24666e40c1cb6bda983b40376c", "fetched_at": "2026-08-29T09:23:53.537588+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/llm-compressor/en/latest/getting-started/install"}, {"content_hash": "56a03c6d3d74dc50afb213d4a5b12ab572b8c9ee0c9bb8b7738a0544e372187c", "fetched_at": "2026-08-29T09:23:53.539461+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/llm-compressor/en/latest/faq/faq"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T18:29:15.664794+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "dfc04828c70aa6203e1ddb95f06af2a14afc215d26803b923031c6371d94d6e9", "fetched_at": "2026-08-28T04:08:15.663534+00:00", "kind": "readme", "missing": false, "url": "https://github.com/vllm-project/llm-compressor"}, {"content_hash": "af790c8b7937deeeab6d99eaa6085101e5f3871fe36b16dee87764c7aeb6f089", "fetched_at": "2026-08-29T09:23:53.532677+00:00", "kind": "homepage", "missing": false, "url": "https://docs.vllm.ai/projects/llm-compressor"}, {"content_hash": "563d18d8696d5d2e5ce52d2b0cc971d87cbfb081c45b7c9135cab0bb3cdd69e4", "fetched_at": "2026-08-29T09:23:53.535623+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/llm-compressor/en/latest/getting-started"}, {"content_hash": "325a3fd81fbe1493e038ee3cb8f05b990544fa24666e40c1cb6bda983b40376c", "fetched_at": "2026-08-29T09:23:53.537588+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/llm-compressor/en/latest/getting-started/install"}, {"content_hash": "56a03c6d3d74dc50afb213d4a5b12ab572b8c9ee0c9bb8b7738a0544e372187c", "fetched_at": "2026-08-29T09:23:53.539461+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/llm-compressor/en/latest/faq/faq"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T18:29:15.664794+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "dfc04828c70aa6203e1ddb95f06af2a14afc215d26803b923031c6371d94d6e9", "fetched_at": "2026-08-28T04:08:15.663534+00:00", "kind": "readme", "missing": false, "url": "https://github.com/vllm-project/llm-compressor"}, {"content_hash": "af790c8b7937deeeab6d99eaa6085101e5f3871fe36b16dee87764c7aeb6f089", "fetched_at": "2026-08-29T09:23:53.532677+00:00", "kind": "homepage", "missing": false, "url": "https://docs.vllm.ai/projects/llm-compressor"}, {"content_hash": "563d18d8696d5d2e5ce52d2b0cc971d87cbfb081c45b7c9135cab0bb3cdd69e4", "fetched_at": "2026-08-29T09:23:53.535623+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/llm-compressor/en/latest/getting-started"}, {"content_hash": "325a3fd81fbe1493e038ee3cb8f05b990544fa24666e40c1cb6bda983b40376c", "fetched_at": "2026-08-29T09:23:53.537588+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/llm-compressor/en/latest/getting-started/install"}, {"content_hash": "56a03c6d3d74dc50afb213d4a5b12ab572b8c9ee0c9bb8b7738a0544e372187c", "fetched_at": "2026-08-29T09:23:53.539461+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/llm-compressor/en/latest/faq/faq"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T18:29:15.664794+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "dfc04828c70aa6203e1ddb95f06af2a14afc215d26803b923031c6371d94d6e9", "fetched_at": "2026-08-28T04:08:15.663534+00:00", "kind": "readme", "missing": false, "url": "https://github.com/vllm-project/llm-compressor"}, {"content_hash": "af790c8b7937deeeab6d99eaa6085101e5f3871fe36b16dee87764c7aeb6f089", "fetched_at": "2026-08-29T09:23:53.532677+00:00", "kind": "homepage", "missing": false, "url": "https://docs.vllm.ai/projects/llm-compressor"}, {"content_hash": "563d18d8696d5d2e5ce52d2b0cc971d87cbfb081c45b7c9135cab0bb3cdd69e4", "fetched_at": "2026-08-29T09:23:53.535623+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/llm-compressor/en/latest/getting-started"}, {"content_hash": "325a3fd81fbe1493e038ee3cb8f05b990544fa24666e40c1cb6bda983b40376c", "fetched_at": "2026-08-29T09:23:53.537588+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/llm-compressor/en/latest/getting-started/install"}, {"content_hash": "56a03c6d3d74dc50afb213d4a5b12ab572b8c9ee0c9bb8b7738a0544e372187c", "fetched_at": "2026-08-29T09:23:53.539461+00:00", "kind": "site_page", "missing": false, "url": "https://docs.vllm.ai/projects/llm-compressor/en/latest/faq/faq"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "longevity": 57, "rhythm": 97}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 804, "days_push": 7, "days_rel": 22, "gap_med": 23.0, "n_releases_24m": 31}, "score": 90, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}