{"adoption": {"forks": 207, "observed_at": "2026-08-28T04:06:40.879808+00:00", "stars": 2360}, "canonical_url": "https://ross.abutalabs.com/products/gptq", "card": {"archived": false, "artifact_type": "library", "description": "Code for the ICLR 2023 paper \"GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers\".", "domain": ["large-language-models", "deep-learning", "machine-learning", "gpu-computing"], "enriched": true, "function": ["llm-inference", "machine-learning", "benchmarking", "gpu-computing"], "health_score": 20, "homepage": "https://arxiv.org/abs/2210.17323", "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["IST-DASLab/gptq"], "name": "IST-DASLab/gptq", "platform": ["python", "cli"], "pushed_at": "2024-03-27T01:46:02+00:00", "repo": "IST-DASLab/gptq", "stars": 2360, "tags": ["quantization", "post-training-quantization", "model-compression", "transformers", "cuda-kernels", "research-code", "iclr-2023", "gpu", "linux"], "topics": [], "urls": [], "use_cases": ["quantize a large language model to 4-bit or 3-bit weights", "run a 175B-parameter model on a single GPU", "compress OPT or BLOOM models with weight grouping", "evaluate perplexity of quantized language models", "benchmark quantized matrix-vector product CUDA kernels", "apply act-order and true-sequential quantization to LLaMA"], "what_it_is": "Reference implementation of GPTQ, a one-shot post-training weight quantization method for large generative transformer models based on approximate second-order information. It quantizes models like OPT, BLOOM, and LLaMA to 2/3/4 bits with minimal accuracy loss and includes CUDA kernels for fast quantized inference.", "when_to_avoid": ["you need a maintained production quantization library with broad model support", "you want easy integration with modern inference frameworks", "you need quantization of non-transformer architectures"], "when_to_choose": ["you need research-grade GPTQ quantization of OPT, BLOOM, or LLaMA models", "you want to reproduce the ICLR 2023 GPTQ paper results", "you need fast 3-bit CUDA kernels for generative inference"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/gptq", "repo": "IST-DASLab/gptq", "role": "main", "score": 32}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:06:40.879808+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T02:36:07.524258+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "82c8bcc1264becceb8b5f4d59daaa5d969648f28470b6e174a3ae9911e5fce24", "fetched_at": "2026-08-28T04:06:40.879808+00:00", "kind": "readme", "missing": false, "url": "https://github.com/IST-DASLab/gptq"}, {"content_hash": "a5080018a865c7c0fcaf9cd62a85934e459ce934cea88fc896640104cb89af1d", "fetched_at": "2026-08-29T10:16:43.736316+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2210.17323"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T10:16:43.745602+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T10:16:43.753134+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T10:16:43.755046+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T10:16:43.750637+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:06:40.879808+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T02:36:07.524258+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "82c8bcc1264becceb8b5f4d59daaa5d969648f28470b6e174a3ae9911e5fce24", "fetched_at": "2026-08-28T04:06:40.879808+00:00", "kind": "readme", "missing": false, "url": "https://github.com/IST-DASLab/gptq"}, {"content_hash": "a5080018a865c7c0fcaf9cd62a85934e459ce934cea88fc896640104cb89af1d", "fetched_at": "2026-08-29T10:16:43.736316+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2210.17323"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T10:16:43.745602+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T10:16:43.753134+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T10:16:43.755046+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T10:16:43.750637+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T02:36:07.524258+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "82c8bcc1264becceb8b5f4d59daaa5d969648f28470b6e174a3ae9911e5fce24", "fetched_at": "2026-08-28T04:06:40.879808+00:00", "kind": "readme", "missing": false, "url": "https://github.com/IST-DASLab/gptq"}, {"content_hash": "a5080018a865c7c0fcaf9cd62a85934e459ce934cea88fc896640104cb89af1d", "fetched_at": "2026-08-29T10:16:43.736316+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2210.17323"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T10:16:43.745602+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T10:16:43.753134+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T10:16:43.755046+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T10:16:43.750637+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:06:40.879808+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:06:40.879808+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:06:40.879808+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T02:36:07.524258+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "82c8bcc1264becceb8b5f4d59daaa5d969648f28470b6e174a3ae9911e5fce24", "fetched_at": "2026-08-28T04:06:40.879808+00:00", "kind": "readme", "missing": false, "url": "https://github.com/IST-DASLab/gptq"}, {"content_hash": "a5080018a865c7c0fcaf9cd62a85934e459ce934cea88fc896640104cb89af1d", "fetched_at": "2026-08-29T10:16:43.736316+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2210.17323"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T10:16:43.745602+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T10:16:43.753134+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T10:16:43.755046+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T10:16:43.750637+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:06:40.879808+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:06:40.879808+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T02:36:07.524258+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "82c8bcc1264becceb8b5f4d59daaa5d969648f28470b6e174a3ae9911e5fce24", "fetched_at": "2026-08-28T04:06:40.879808+00:00", "kind": "readme", "missing": false, "url": "https://github.com/IST-DASLab/gptq"}, {"content_hash": "a5080018a865c7c0fcaf9cd62a85934e459ce934cea88fc896640104cb89af1d", "fetched_at": "2026-08-29T10:16:43.736316+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2210.17323"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T10:16:43.745602+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T10:16:43.753134+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T10:16:43.755046+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T10:16:43.750637+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:06:40.879808+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:06:40.879808+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:06:40.879808+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T02:36:07.524258+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "82c8bcc1264becceb8b5f4d59daaa5d969648f28470b6e174a3ae9911e5fce24", "fetched_at": "2026-08-28T04:06:40.879808+00:00", "kind": "readme", "missing": false, "url": "https://github.com/IST-DASLab/gptq"}, {"content_hash": "a5080018a865c7c0fcaf9cd62a85934e459ce934cea88fc896640104cb89af1d", "fetched_at": "2026-08-29T10:16:43.736316+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2210.17323"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T10:16:43.745602+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T10:16:43.753134+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T10:16:43.755046+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T10:16:43.750637+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:06:40.879808+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:06:40.879808+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T02:36:07.524258+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "82c8bcc1264becceb8b5f4d59daaa5d969648f28470b6e174a3ae9911e5fce24", "fetched_at": "2026-08-28T04:06:40.879808+00:00", "kind": "readme", "missing": false, "url": "https://github.com/IST-DASLab/gptq"}, {"content_hash": "a5080018a865c7c0fcaf9cd62a85934e459ce934cea88fc896640104cb89af1d", "fetched_at": "2026-08-29T10:16:43.736316+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2210.17323"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T10:16:43.745602+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T10:16:43.753134+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T10:16:43.755046+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T10:16:43.750637+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T02:36:07.524258+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "82c8bcc1264becceb8b5f4d59daaa5d969648f28470b6e174a3ae9911e5fce24", "fetched_at": "2026-08-28T04:06:40.879808+00:00", "kind": "readme", "missing": false, "url": "https://github.com/IST-DASLab/gptq"}, {"content_hash": "a5080018a865c7c0fcaf9cd62a85934e459ce934cea88fc896640104cb89af1d", "fetched_at": "2026-08-29T10:16:43.736316+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2210.17323"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T10:16:43.745602+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T10:16:43.753134+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T10:16:43.755046+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T10:16:43.750637+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T02:36:07.524258+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "82c8bcc1264becceb8b5f4d59daaa5d969648f28470b6e174a3ae9911e5fce24", "fetched_at": "2026-08-28T04:06:40.879808+00:00", "kind": "readme", "missing": false, "url": "https://github.com/IST-DASLab/gptq"}, {"content_hash": "a5080018a865c7c0fcaf9cd62a85934e459ce934cea88fc896640104cb89af1d", "fetched_at": "2026-08-29T10:16:43.736316+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2210.17323"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T10:16:43.745602+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T10:16:43.753134+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T10:16:43.755046+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T10:16:43.750637+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T02:36:07.524258+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "82c8bcc1264becceb8b5f4d59daaa5d969648f28470b6e174a3ae9911e5fce24", "fetched_at": "2026-08-28T04:06:40.879808+00:00", "kind": "readme", "missing": false, "url": "https://github.com/IST-DASLab/gptq"}, {"content_hash": "a5080018a865c7c0fcaf9cd62a85934e459ce934cea88fc896640104cb89af1d", "fetched_at": "2026-08-29T10:16:43.736316+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2210.17323"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T10:16:43.745602+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T10:16:43.753134+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T10:16:43.755046+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T10:16:43.750637+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 1414, "days_push": 890, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 32, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}