{"adoption": {"forks": 206, "observed_at": "2026-08-28T04:05:21.038115+00:00", "stars": 1677}, "canonical_url": "https://ross.abutalabs.com/products/smoothquant", "card": {"archived": false, "artifact_type": "library", "description": "[ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models", "domain": ["large-language-models", "machine-learning", "deep-learning"], "enriched": true, "function": ["llm-inference", "machine-learning", "deep-learning"], "health_score": 20, "homepage": "https://arxiv.org/abs/2211.10438", "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["mit-han-lab/smoothquant"], "name": "mit-han-lab/smoothquant", "platform": ["python"], "pushed_at": "2024-07-12T03:11:08+00:00", "repo": "mit-han-lab/smoothquant", "stars": 1677, "tags": ["quantization", "post-training-quantization", "w8a8", "int8", "model-compression", "inference-optimization", "research-paper", "gpu", "linux"], "topics": [], "urls": [], "use_cases": ["quantize an LLM to int8 weights and activations without retraining", "reduce GPU memory usage for serving large language models", "speed up LLM inference with W8A8 quantization", "serve a 530B parameter model on a single node", "evaluate quantization accuracy on Llama, Falcon, Mistral, or Mixtral models", "integrate activation-smoothing quantization into an inference engine"], "what_it_is": "SmoothQuant is a training-free post-training quantization (PTQ) method that enables W8A8 (8-bit weight, 8-bit activation) quantization for large language models by migrating quantization difficulty from activations to weights. This repository provides the reference Python implementation, supporting models like OPT, BLOOM, GLM, Llama, Falcon, Mistral, and Mixtral with up to 1.56x speedup and 2x memory reduction.", "when_to_avoid": ["you need 4-bit or lower-bit quantization rather than 8-bit", "you require a production-maintained integration - use TensorRT-LLM, ONNX Runtime, or Neural-Compressor which have adopted SmoothQuant", "you are quantizing small models where activation outliers are not a problem"], "when_to_choose": ["you need training-free W8A8 quantization of large language models with minimal accuracy loss", "you want to reduce memory footprint and hardware costs for LLM serving", "you are researching or benchmarking post-training quantization methods for LLMs"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/smoothquant", "repo": "mit-han-lab/smoothquant", "role": "main", "score": 32}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:05:21.038115+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T03:41:37.128036+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6af10e2a4a7fdf0201773c7b7ce371b07b09ca4c3298481ac85d5a626a163af8", "fetched_at": "2026-08-28T04:05:21.038115+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mit-han-lab/smoothquant"}, {"content_hash": "4ea8851b899ea3db8eb2f960d1b9a2ea016aac569501dc3250917e9368b4f8f8", "fetched_at": "2026-08-29T11:15:03.223160+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2211.10438"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T11:15:03.225801+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T11:15:03.229102+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T11:15:03.230888+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T11:15:03.227544+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:05:21.038115+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T03:41:37.128036+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6af10e2a4a7fdf0201773c7b7ce371b07b09ca4c3298481ac85d5a626a163af8", "fetched_at": "2026-08-28T04:05:21.038115+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mit-han-lab/smoothquant"}, {"content_hash": "4ea8851b899ea3db8eb2f960d1b9a2ea016aac569501dc3250917e9368b4f8f8", "fetched_at": "2026-08-29T11:15:03.223160+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2211.10438"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T11:15:03.225801+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T11:15:03.229102+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T11:15:03.230888+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T11:15:03.227544+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": "2026-08-30T03:41:37.128036+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6af10e2a4a7fdf0201773c7b7ce371b07b09ca4c3298481ac85d5a626a163af8", "fetched_at": "2026-08-28T04:05:21.038115+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mit-han-lab/smoothquant"}, {"content_hash": "4ea8851b899ea3db8eb2f960d1b9a2ea016aac569501dc3250917e9368b4f8f8", "fetched_at": "2026-08-29T11:15:03.223160+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2211.10438"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T11:15:03.225801+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T11:15:03.229102+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T11:15:03.230888+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T11:15:03.227544+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": "2026-08-28T04:05:21.038115+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:05:21.038115+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:05:21.038115+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T03:41:37.128036+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6af10e2a4a7fdf0201773c7b7ce371b07b09ca4c3298481ac85d5a626a163af8", "fetched_at": "2026-08-28T04:05:21.038115+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mit-han-lab/smoothquant"}, {"content_hash": "4ea8851b899ea3db8eb2f960d1b9a2ea016aac569501dc3250917e9368b4f8f8", "fetched_at": "2026-08-29T11:15:03.223160+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2211.10438"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T11:15:03.225801+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T11:15:03.229102+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T11:15:03.230888+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T11:15:03.227544+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:05:21.038115+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:05:21.038115+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T03:41:37.128036+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6af10e2a4a7fdf0201773c7b7ce371b07b09ca4c3298481ac85d5a626a163af8", "fetched_at": "2026-08-28T04:05:21.038115+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mit-han-lab/smoothquant"}, {"content_hash": "4ea8851b899ea3db8eb2f960d1b9a2ea016aac569501dc3250917e9368b4f8f8", "fetched_at": "2026-08-29T11:15:03.223160+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2211.10438"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T11:15:03.225801+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T11:15:03.229102+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T11:15:03.230888+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T11:15:03.227544+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:05:21.038115+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:05:21.038115+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:05:21.038115+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T03:41:37.128036+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6af10e2a4a7fdf0201773c7b7ce371b07b09ca4c3298481ac85d5a626a163af8", "fetched_at": "2026-08-28T04:05:21.038115+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mit-han-lab/smoothquant"}, {"content_hash": "4ea8851b899ea3db8eb2f960d1b9a2ea016aac569501dc3250917e9368b4f8f8", "fetched_at": "2026-08-29T11:15:03.223160+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2211.10438"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T11:15:03.225801+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T11:15:03.229102+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T11:15:03.230888+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T11:15:03.227544+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:05:21.038115+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:05:21.038115+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T03:41:37.128036+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6af10e2a4a7fdf0201773c7b7ce371b07b09ca4c3298481ac85d5a626a163af8", "fetched_at": "2026-08-28T04:05:21.038115+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mit-han-lab/smoothquant"}, {"content_hash": "4ea8851b899ea3db8eb2f960d1b9a2ea016aac569501dc3250917e9368b4f8f8", "fetched_at": "2026-08-29T11:15:03.223160+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2211.10438"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T11:15:03.225801+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T11:15:03.229102+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T11:15:03.230888+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T11:15:03.227544+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": "2026-08-30T03:41:37.128036+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6af10e2a4a7fdf0201773c7b7ce371b07b09ca4c3298481ac85d5a626a163af8", "fetched_at": "2026-08-28T04:05:21.038115+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mit-han-lab/smoothquant"}, {"content_hash": "4ea8851b899ea3db8eb2f960d1b9a2ea016aac569501dc3250917e9368b4f8f8", "fetched_at": "2026-08-29T11:15:03.223160+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2211.10438"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T11:15:03.225801+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T11:15:03.229102+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T11:15:03.230888+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T11:15:03.227544+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": "2026-08-30T03:41:37.128036+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6af10e2a4a7fdf0201773c7b7ce371b07b09ca4c3298481ac85d5a626a163af8", "fetched_at": "2026-08-28T04:05:21.038115+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mit-han-lab/smoothquant"}, {"content_hash": "4ea8851b899ea3db8eb2f960d1b9a2ea016aac569501dc3250917e9368b4f8f8", "fetched_at": "2026-08-29T11:15:03.223160+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2211.10438"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T11:15:03.225801+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T11:15:03.229102+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T11:15:03.230888+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T11:15:03.227544+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": "2026-08-30T03:41:37.128036+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6af10e2a4a7fdf0201773c7b7ce371b07b09ca4c3298481ac85d5a626a163af8", "fetched_at": "2026-08-28T04:05:21.038115+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mit-han-lab/smoothquant"}, {"content_hash": "4ea8851b899ea3db8eb2f960d1b9a2ea016aac569501dc3250917e9368b4f8f8", "fetched_at": "2026-08-29T11:15:03.223160+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2211.10438"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T11:15:03.225801+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T11:15:03.229102+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T11:15:03.230888+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T11:15:03.227544+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 98, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 1385, "days_push": 782, "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}}