{"adoption": {"forks": 321, "observed_at": "2026-08-28T04:08:11.857435+00:00", "stars": 3621}, "canonical_url": "https://ross.abutalabs.com/products/llm-awq", "card": {"archived": false, "artifact_type": "library", "description": "[MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration", "domain": ["large-language-models", "machine-learning", "gpu-computing", "developer-tools"], "enriched": true, "function": ["llm-inference", "machine-learning", "gpu-computing", "benchmarking"], "health_score": 39, "homepage": null, "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["mit-han-lab/llm-awq"], "name": "mit-han-lab/llm-awq", "platform": ["python", "cross-platform"], "pushed_at": "2025-07-17T19:44:51+00:00", "repo": "mit-han-lab/llm-awq", "stars": 3621, "tags": ["quantization", "weight-quantization", "int4", "model-compression", "inference-optimization", "edge-inference", "cuda-kernels", "vision-language-models", "gpu", "linux"], "topics": [], "urls": [], "use_cases": ["quantize llama models to 4-bit", "run llm inference on jetson edge device", "compress large language models to fit in limited gpu memory", "speed up llm inference with 4-bit weights", "run vision language model on low-power hardware", "quantize deepseek distilled models", "offline on-device chatbot inference"], "what_it_is": "AWQ is a Python library implementing Activation-aware Weight Quantization for compressing large language models to low-bit (INT3/4) weights with efficient CUDA inference kernels. It includes a model zoo of pre-quantized LLMs and TinyChat, a turn-key on-device inference engine for LLMs and vision-language models on edge devices.", "when_to_avoid": ["you need quantization of non-LLM model types", "you need CPU-only inference without NVIDIA GPUs", "you need training or fine-tuning rather than inference compression"], "when_to_choose": ["you need to run LLMs or VLMs on memory-constrained GPUs or edge devices like Jetson", "you want accurate INT4 weight-only quantization with fast CUDA kernels", "you want pre-quantized model checkpoints for popular LLM families"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/llm-awq", "repo": "mit-han-lab/llm-awq", "role": "main", "score": 44}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:08:11.857435+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T18:31:58.067855+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "970c98b603829fde90c362d6e2588c8845c465f2286a7af044616f8c70cfaf27", "fetched_at": "2026-08-28T04:08:11.857435+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mit-han-lab/llm-awq"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:08:11.857435+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T18:31:58.067855+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "970c98b603829fde90c362d6e2588c8845c465f2286a7af044616f8c70cfaf27", "fetched_at": "2026-08-28T04:08:11.857435+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mit-han-lab/llm-awq"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T18:31:58.067855+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "970c98b603829fde90c362d6e2588c8845c465f2286a7af044616f8c70cfaf27", "fetched_at": "2026-08-28T04:08:11.857435+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mit-han-lab/llm-awq"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:08:11.857435+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:08:11.857435+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:08:11.857435+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T18:31:58.067855+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "970c98b603829fde90c362d6e2588c8845c465f2286a7af044616f8c70cfaf27", "fetched_at": "2026-08-28T04:08:11.857435+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mit-han-lab/llm-awq"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:08:11.857435+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:08:11.857435+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T18:31:58.067855+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "970c98b603829fde90c362d6e2588c8845c465f2286a7af044616f8c70cfaf27", "fetched_at": "2026-08-28T04:08:11.857435+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mit-han-lab/llm-awq"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:08:11.857435+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:08:11.857435+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:08:11.857435+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T18:31:58.067855+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "970c98b603829fde90c362d6e2588c8845c465f2286a7af044616f8c70cfaf27", "fetched_at": "2026-08-28T04:08:11.857435+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mit-han-lab/llm-awq"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:08:11.857435+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:08:11.857435+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T18:31:58.067855+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "970c98b603829fde90c362d6e2588c8845c465f2286a7af044616f8c70cfaf27", "fetched_at": "2026-08-28T04:08:11.857435+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mit-han-lab/llm-awq"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T18:31:58.067855+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "970c98b603829fde90c362d6e2588c8845c465f2286a7af044616f8c70cfaf27", "fetched_at": "2026-08-28T04:08:11.857435+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mit-han-lab/llm-awq"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T18:31:58.067855+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "970c98b603829fde90c362d6e2588c8845c465f2286a7af044616f8c70cfaf27", "fetched_at": "2026-08-28T04:08:11.857435+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mit-han-lab/llm-awq"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T18:31:58.067855+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "970c98b603829fde90c362d6e2588c8845c465f2286a7af044616f8c70cfaf27", "fetched_at": "2026-08-28T04:08:11.857435+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mit-han-lab/llm-awq"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 32, "longevity": 85, "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": 1190, "days_push": 412, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 44, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}