{"adoption": {"forks": 320, "observed_at": "2026-08-28T04:07:11.573877+00:00", "stars": 2704}, "canonical_url": "https://ross.abutalabs.com/products/neural-compressor", "card": {"archived": false, "artifact_type": "library", "description": "SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime", "domain": ["machine-learning", "deep-learning", "large-language-models", "developer-tools"], "enriched": true, "function": ["machine-learning", "deep-learning", "llm-inference", "llm-training"], "health_score": 99, "homepage": "https://intel.github.io/neural-compressor/", "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["intel/neural-compressor"], "name": "intel/neural-compressor", "platform": ["python", "cross-platform"], "pushed_at": "2026-08-26T08:40:37+00:00", "repo": "intel/neural-compressor", "stars": 2704, "tags": ["quantization", "model-compression", "sparsity", "pruning", "knowledge-distillation", "post-training-quantization", "quantization-aware-training", "smoothquant", "gptq", "awq", "int8", "int4", "fp8", "mxfp4", "pytorch", "tensorflow", "onnx-runtime", "intel-hardware", "linux", "gpu"], "topics": ["low-precision", "pruning", "sparsity", "auto-tuning", "knowledge-distillation", "quantization", "quantization-aware-training", "post-training-quantization", "smoothquant", "large-language-models", "awq", "fp4", "gptq", "int4", "int8", "mxformat", "sparsegpt"], "urls": [], "use_cases": ["quantize an LLM to INT4 or FP8 for faster inference", "apply SmoothQuant or GPTQ to compress a large language model", "run post-training quantization on a PyTorch model", "prune or sparsify a deep learning model", "optimize models for Intel Xeon CPUs or Gaudi accelerators", "quantize models to MXFP4 or NVFP4 low-precision formats", "compress a vision-language model like LLaMA or Qwen", "perform quantization-aware training on TensorFlow models"], "what_it_is": "Intel Neural Compressor is an open-source Python library providing state-of-the-art low-bit quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4), sparsity, and other model compression techniques for deep learning frameworks including PyTorch, TensorFlow, JAX, and ONNX Runtime. It supports advanced quantization of large language models and vision-language models with extensive optimization for Intel hardware (Gaudi, Xeon, Core Ultra, Data Center GPUs) and limited support for AMD, ARM, and NVIDIA hardware.", "when_to_avoid": ["you only target NVIDIA GPUs and prefer ecosystem-native tools like TensorRT-LLM", "you need a simple one-line quantization without tuning and prefer lighter-weight tools like AutoRound directly", "your framework is outside PyTorch, TensorFlow, JAX, or ONNX Runtime"], "when_to_choose": ["you need low-bit quantization of LLMs or VLMs across multiple data types", "you target Intel hardware (Gaudi, Xeon, Core Ultra, Data Center GPUs) for inference optimization", "you work across PyTorch, TensorFlow, JAX, or ONNX Runtime and want a unified compression API", "you need sparsity, pruning, or knowledge distillation alongside quantization"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/neural-compressor", "repo": "intel/neural-compressor", "role": "main", "score": 92}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:07:11.573877+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T02:15:54.095366+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a586ca19d72224406a45b0aa4aa453d5c98ba1ab46a2e41a6eed21b4752a2107", "fetched_at": "2026-08-28T04:07:11.573877+00:00", "kind": "readme", "missing": false, "url": "https://github.com/intel/neural-compressor"}, {"content_hash": "44136fa355b3678a1146ad16f7e8649e94fb4fc21fe77e8310c060f61caaff8a", "fetched_at": "2026-08-29T09:58:53.987377+00:00", "kind": "homepage", "missing": false, "url": "https://intel.github.io/neural-compressor/"}, {"content_hash": "2dfca99a671dbc65186b92e5b774dfa9ecf3a5cba8278509cac1e056f0f89cf5", "fetched_at": "2026-08-29T09:58:53.996188+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/neural-compressor/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:07:11.573877+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T02:15:54.095366+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a586ca19d72224406a45b0aa4aa453d5c98ba1ab46a2e41a6eed21b4752a2107", "fetched_at": "2026-08-28T04:07:11.573877+00:00", "kind": "readme", "missing": false, "url": "https://github.com/intel/neural-compressor"}, {"content_hash": "44136fa355b3678a1146ad16f7e8649e94fb4fc21fe77e8310c060f61caaff8a", "fetched_at": "2026-08-29T09:58:53.987377+00:00", "kind": "homepage", "missing": false, "url": "https://intel.github.io/neural-compressor/"}, {"content_hash": "2dfca99a671dbc65186b92e5b774dfa9ecf3a5cba8278509cac1e056f0f89cf5", "fetched_at": "2026-08-29T09:58:53.996188+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/neural-compressor/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T02:15:54.095366+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a586ca19d72224406a45b0aa4aa453d5c98ba1ab46a2e41a6eed21b4752a2107", "fetched_at": "2026-08-28T04:07:11.573877+00:00", "kind": "readme", "missing": false, "url": "https://github.com/intel/neural-compressor"}, {"content_hash": "44136fa355b3678a1146ad16f7e8649e94fb4fc21fe77e8310c060f61caaff8a", "fetched_at": "2026-08-29T09:58:53.987377+00:00", "kind": "homepage", "missing": false, "url": "https://intel.github.io/neural-compressor/"}, {"content_hash": "2dfca99a671dbc65186b92e5b774dfa9ecf3a5cba8278509cac1e056f0f89cf5", "fetched_at": "2026-08-29T09:58:53.996188+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/neural-compressor/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:07:11.573877+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:07:11.573877+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:07:11.573877+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T02:15:54.095366+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a586ca19d72224406a45b0aa4aa453d5c98ba1ab46a2e41a6eed21b4752a2107", "fetched_at": "2026-08-28T04:07:11.573877+00:00", "kind": "readme", "missing": false, "url": "https://github.com/intel/neural-compressor"}, {"content_hash": "44136fa355b3678a1146ad16f7e8649e94fb4fc21fe77e8310c060f61caaff8a", "fetched_at": "2026-08-29T09:58:53.987377+00:00", "kind": "homepage", "missing": false, "url": "https://intel.github.io/neural-compressor/"}, {"content_hash": "2dfca99a671dbc65186b92e5b774dfa9ecf3a5cba8278509cac1e056f0f89cf5", "fetched_at": "2026-08-29T09:58:53.996188+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/neural-compressor/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:07:11.573877+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:07:11.573877+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T02:15:54.095366+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a586ca19d72224406a45b0aa4aa453d5c98ba1ab46a2e41a6eed21b4752a2107", "fetched_at": "2026-08-28T04:07:11.573877+00:00", "kind": "readme", "missing": false, "url": "https://github.com/intel/neural-compressor"}, {"content_hash": "44136fa355b3678a1146ad16f7e8649e94fb4fc21fe77e8310c060f61caaff8a", "fetched_at": "2026-08-29T09:58:53.987377+00:00", "kind": "homepage", "missing": false, "url": "https://intel.github.io/neural-compressor/"}, {"content_hash": "2dfca99a671dbc65186b92e5b774dfa9ecf3a5cba8278509cac1e056f0f89cf5", "fetched_at": "2026-08-29T09:58:53.996188+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/neural-compressor/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:07:11.573877+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:07:11.573877+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:07:11.573877+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T02:15:54.095366+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a586ca19d72224406a45b0aa4aa453d5c98ba1ab46a2e41a6eed21b4752a2107", "fetched_at": "2026-08-28T04:07:11.573877+00:00", "kind": "readme", "missing": false, "url": "https://github.com/intel/neural-compressor"}, {"content_hash": "44136fa355b3678a1146ad16f7e8649e94fb4fc21fe77e8310c060f61caaff8a", "fetched_at": "2026-08-29T09:58:53.987377+00:00", "kind": "homepage", "missing": false, "url": "https://intel.github.io/neural-compressor/"}, {"content_hash": "2dfca99a671dbc65186b92e5b774dfa9ecf3a5cba8278509cac1e056f0f89cf5", "fetched_at": "2026-08-29T09:58:53.996188+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/neural-compressor/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:07:11.573877+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:07:11.573877+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T02:15:54.095366+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a586ca19d72224406a45b0aa4aa453d5c98ba1ab46a2e41a6eed21b4752a2107", "fetched_at": "2026-08-28T04:07:11.573877+00:00", "kind": "readme", "missing": false, "url": "https://github.com/intel/neural-compressor"}, {"content_hash": "44136fa355b3678a1146ad16f7e8649e94fb4fc21fe77e8310c060f61caaff8a", "fetched_at": "2026-08-29T09:58:53.987377+00:00", "kind": "homepage", "missing": false, "url": "https://intel.github.io/neural-compressor/"}, {"content_hash": "2dfca99a671dbc65186b92e5b774dfa9ecf3a5cba8278509cac1e056f0f89cf5", "fetched_at": "2026-08-29T09:58:53.996188+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/neural-compressor/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T02:15:54.095366+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a586ca19d72224406a45b0aa4aa453d5c98ba1ab46a2e41a6eed21b4752a2107", "fetched_at": "2026-08-28T04:07:11.573877+00:00", "kind": "readme", "missing": false, "url": "https://github.com/intel/neural-compressor"}, {"content_hash": "44136fa355b3678a1146ad16f7e8649e94fb4fc21fe77e8310c060f61caaff8a", "fetched_at": "2026-08-29T09:58:53.987377+00:00", "kind": "homepage", "missing": false, "url": "https://intel.github.io/neural-compressor/"}, {"content_hash": "2dfca99a671dbc65186b92e5b774dfa9ecf3a5cba8278509cac1e056f0f89cf5", "fetched_at": "2026-08-29T09:58:53.996188+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/neural-compressor/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T02:15:54.095366+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a586ca19d72224406a45b0aa4aa453d5c98ba1ab46a2e41a6eed21b4752a2107", "fetched_at": "2026-08-28T04:07:11.573877+00:00", "kind": "readme", "missing": false, "url": "https://github.com/intel/neural-compressor"}, {"content_hash": "44136fa355b3678a1146ad16f7e8649e94fb4fc21fe77e8310c060f61caaff8a", "fetched_at": "2026-08-29T09:58:53.987377+00:00", "kind": "homepage", "missing": false, "url": "https://intel.github.io/neural-compressor/"}, {"content_hash": "2dfca99a671dbc65186b92e5b774dfa9ecf3a5cba8278509cac1e056f0f89cf5", "fetched_at": "2026-08-29T09:58:53.996188+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/neural-compressor/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T02:15:54.095366+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a586ca19d72224406a45b0aa4aa453d5c98ba1ab46a2e41a6eed21b4752a2107", "fetched_at": "2026-08-28T04:07:11.573877+00:00", "kind": "readme", "missing": false, "url": "https://github.com/intel/neural-compressor"}, {"content_hash": "44136fa355b3678a1146ad16f7e8649e94fb4fc21fe77e8310c060f61caaff8a", "fetched_at": "2026-08-29T09:58:53.987377+00:00", "kind": "homepage", "missing": false, "url": "https://intel.github.io/neural-compressor/"}, {"content_hash": "2dfca99a671dbc65186b92e5b774dfa9ecf3a5cba8278509cac1e056f0f89cf5", "fetched_at": "2026-08-29T09:58:53.996188+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/neural-compressor/json"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "longevity": 100, "rhythm": 79}, "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": 2234, "days_push": 7, "days_rel": 63, "gap_med": 64.5, "n_releases_24m": 9}, "score": 92, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}