{"adoption": {"forks": 168, "observed_at": "2026-08-28T04:05:07.919549+00:00", "stars": 1588}, "canonical_url": "https://ross.abutalabs.com/products/auto-round", "card": {"archived": false, "artifact_type": "library", "description": "A SOTA quantization toolkit for high-accuracy low-bit LLM inference, seamlessly optimized for CPU/XPU/CUDA, with multi-datatype support and full compatibility with vLLM, SGLang, and Transformers|简洁且高效的量化工具包", "domain": ["large-language-models", "machine-learning", "deep-learning", "developer-tools"], "enriched": true, "function": ["llm-inference", "machine-learning", "cli", "sdk"], "health_score": 100, "homepage": null, "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["intel/auto-round"], "name": "intel/auto-round", "platform": ["python", "windows"], "pushed_at": "2026-08-26T15:29:11+00:00", "repo": "intel/auto-round", "stars": 1588, "tags": ["quantization", "int4", "low-bit-quantization", "signround", "vllm", "sglang", "gguf", "mxfp4", "nvfp4", "vision-language-models", "weight-only-quantization", "model-compression", "linux", "macos", "gpu", "cpu"], "topics": ["int4", "quantization", "rounding", "transformers", "vllm", "mxfp4", "nvfp4", "gguf", "sglang", "llms", "vlms", "diffusers", "omni"], "urls": [], "use_cases": ["quantize an LLM to int4 for faster inference", "compress a large language model to run on CPU", "convert models to gguf or mxfp4 formats", "quantize a vision-language model with minimal accuracy loss", "prepare quantized models for vLLM or SGLang deployment", "calibration-free low-bit quantization of open LLMs"], "what_it_is": "AutoRound is Intel's advanced quantization toolkit for LLMs and vision-language models, using sign-gradient descent to achieve high accuracy at 2-4 bit widths. It supports multiple datatypes and hardware (CPU, XPU, CUDA) and integrates with vLLM, SGLang, and Hugging Face Transformers.", "when_to_avoid": ["you need quantization for non-transformer model architectures", "you want training-time or QAT quantization rather than post-training weight-only", "you require a fully stable, long-term-supported API given rapid experimental changes"], "when_to_choose": ["you need high-accuracy 2-4 bit weight-only quantization for LLMs or VLMs", "you deploy on Intel CPU/GPU or NVIDIA CUDA and want vLLM/SGLang compatibility", "you want multiple output formats like GGUF, MXFP4, or NVFP4 from one toolkit"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/auto-round", "repo": "intel/auto-round", "role": "main", "score": 91}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:05:07.919549+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T03:55:01.148539+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1d1f96809c9744d3c601720559eb0dce1ce400eb0b5d62c3bb24ca7767ad9f32", "fetched_at": "2026-08-28T04:05:07.919549+00:00", "kind": "readme", "missing": false, "url": "https://github.com/intel/auto-round"}, {"content_hash": "3e09e6bcd0bf473b0a24101fedec5ebb23ede150eb24ff7e263a3eb591c4bdad", "fetched_at": "2026-08-29T11:25:44.509573+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/auto-round/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:05:07.919549+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T03:55:01.148539+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1d1f96809c9744d3c601720559eb0dce1ce400eb0b5d62c3bb24ca7767ad9f32", "fetched_at": "2026-08-28T04:05:07.919549+00:00", "kind": "readme", "missing": false, "url": "https://github.com/intel/auto-round"}, {"content_hash": "3e09e6bcd0bf473b0a24101fedec5ebb23ede150eb24ff7e263a3eb591c4bdad", "fetched_at": "2026-08-29T11:25:44.509573+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/auto-round/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T03:55:01.148539+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1d1f96809c9744d3c601720559eb0dce1ce400eb0b5d62c3bb24ca7767ad9f32", "fetched_at": "2026-08-28T04:05:07.919549+00:00", "kind": "readme", "missing": false, "url": "https://github.com/intel/auto-round"}, {"content_hash": "3e09e6bcd0bf473b0a24101fedec5ebb23ede150eb24ff7e263a3eb591c4bdad", "fetched_at": "2026-08-29T11:25:44.509573+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/auto-round/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:05:07.919549+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:05:07.919549+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:05:07.919549+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T03:55:01.148539+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1d1f96809c9744d3c601720559eb0dce1ce400eb0b5d62c3bb24ca7767ad9f32", "fetched_at": "2026-08-28T04:05:07.919549+00:00", "kind": "readme", "missing": false, "url": "https://github.com/intel/auto-round"}, {"content_hash": "3e09e6bcd0bf473b0a24101fedec5ebb23ede150eb24ff7e263a3eb591c4bdad", "fetched_at": "2026-08-29T11:25:44.509573+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/auto-round/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:05:07.919549+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:05:07.919549+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T03:55:01.148539+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1d1f96809c9744d3c601720559eb0dce1ce400eb0b5d62c3bb24ca7767ad9f32", "fetched_at": "2026-08-28T04:05:07.919549+00:00", "kind": "readme", "missing": false, "url": "https://github.com/intel/auto-round"}, {"content_hash": "3e09e6bcd0bf473b0a24101fedec5ebb23ede150eb24ff7e263a3eb591c4bdad", "fetched_at": "2026-08-29T11:25:44.509573+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/auto-round/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:05:07.919549+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:05:07.919549+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:05:07.919549+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T03:55:01.148539+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1d1f96809c9744d3c601720559eb0dce1ce400eb0b5d62c3bb24ca7767ad9f32", "fetched_at": "2026-08-28T04:05:07.919549+00:00", "kind": "readme", "missing": false, "url": "https://github.com/intel/auto-round"}, {"content_hash": "3e09e6bcd0bf473b0a24101fedec5ebb23ede150eb24ff7e263a3eb591c4bdad", "fetched_at": "2026-08-29T11:25:44.509573+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/auto-round/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:05:07.919549+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:05:07.919549+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T03:55:01.148539+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1d1f96809c9744d3c601720559eb0dce1ce400eb0b5d62c3bb24ca7767ad9f32", "fetched_at": "2026-08-28T04:05:07.919549+00:00", "kind": "readme", "missing": false, "url": "https://github.com/intel/auto-round"}, {"content_hash": "3e09e6bcd0bf473b0a24101fedec5ebb23ede150eb24ff7e263a3eb591c4bdad", "fetched_at": "2026-08-29T11:25:44.509573+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/auto-round/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T03:55:01.148539+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1d1f96809c9744d3c601720559eb0dce1ce400eb0b5d62c3bb24ca7767ad9f32", "fetched_at": "2026-08-28T04:05:07.919549+00:00", "kind": "readme", "missing": false, "url": "https://github.com/intel/auto-round"}, {"content_hash": "3e09e6bcd0bf473b0a24101fedec5ebb23ede150eb24ff7e263a3eb591c4bdad", "fetched_at": "2026-08-29T11:25:44.509573+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/auto-round/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T03:55:01.148539+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1d1f96809c9744d3c601720559eb0dce1ce400eb0b5d62c3bb24ca7767ad9f32", "fetched_at": "2026-08-28T04:05:07.919549+00:00", "kind": "readme", "missing": false, "url": "https://github.com/intel/auto-round"}, {"content_hash": "3e09e6bcd0bf473b0a24101fedec5ebb23ede150eb24ff7e263a3eb591c4bdad", "fetched_at": "2026-08-29T11:25:44.509573+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/auto-round/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T03:55:01.148539+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1d1f96809c9744d3c601720559eb0dce1ce400eb0b5d62c3bb24ca7767ad9f32", "fetched_at": "2026-08-28T04:05:07.919549+00:00", "kind": "readme", "missing": false, "url": "https://github.com/intel/auto-round"}, {"content_hash": "3e09e6bcd0bf473b0a24101fedec5ebb23ede150eb24ff7e263a3eb591c4bdad", "fetched_at": "2026-08-29T11:25:44.509573+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/auto-round/json"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "longevity": 69, "rhythm": 93}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 972, "days_push": 7, "days_rel": 51, "gap_med": 13, "n_releases_24m": 34}, "score": 91, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}