{"full_name":"NVIDIA/Model-Optimizer","owner":"NVIDIA","name":"Model-Optimizer","url":"https://github.com/NVIDIA/Model-Optimizer","description":"A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM, TensorRT, vLLM, etc. to optimize inference speed.","homepage":"https://nvidia.github.io/Model-Optimizer/","topics":[],"language":"Python","license":null,"avatar":"https://avatars.githubusercontent.com/u/1728152?v=4","created_at":"2024-04-24T03:00:54Z","pushed_at":null,"metrics":{"stars":5502,"forks":793,"watchers":33,"issues":null,"prs":null,"releases":54,"issues_open":null,"issues_closed":null,"prs_open":null,"prs_closed":null,"prs_merged":null,"discussions":null},"growth":{"day":{"stars":0,"forks":0,"base_day":"2026-11-04"},"week":{"stars":6,"forks":3,"base_day":"2026-11-03"},"month":{"stars":314,"forks":68,"base_day":"2026-10-11"}},"history":{"dates":["2026-10-04","2026-10-05","2026-10-06","2026-10-07","2026-10-08","2026-10-09","2026-10-10","2026-10-11","2026-10-12","2026-10-13","2026-10-14","2026-10-15","2026-10-16","2026-10-17","2026-10-18","2026-10-19","2026-10-20","2026-10-21","2026-10-22","2026-10-23","2026-10-24","2026-10-25","2026-10-26","2026-10-27","2026-10-28","2026-10-29","2026-10-30","2026-10-31","2026-11-01","2026-11-02","2026-11-03","2026-11-04"],"stars":[4035,4390,4692,5016,5074,5140,5166,5188,5217,5228,5236,5243,5253,5261,5281,5298,5311,5326,5345,5369,5384,5398,5413,5425,5428,5444,5453,5461,5466,5472,5496,5502],"forks":[628,645,664,698,706,715,721,725,729,731,732,736,736,738,738,741,742,747,749,756,760,764,767,769,771,779,781,781,785,789,790,793],"watchers":[33,35,38,36,37,38,37,37,37,37,37,37,37,37,37,37,37,36,36,36,36,35,35,35,35,35,35,35,35,35,34,33],"issues_open":[null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null],"prs_open":[null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null]},"boards":{},"same_owner":[{"full_name":"NVIDIA/DALI","name":"DALI","boards":{}},{"full_name":"NVIDIA/Isaac-GR00T","name":"Isaac-GR00T","boards":{}},{"full_name":"NVIDIA/Megatron-LM","name":"Megatron-LM","boards":{}},{"full_name":"NVIDIA/NemoClaw","name":"NemoClaw","boards":{}},{"full_name":"NVIDIA/OpenShell","name":"OpenShell","boards":{"daily":116,"monthly":86,"daily_rate":110,"monthly_rate":64}},{"full_name":"NVIDIA/SkillSpector","name":"SkillSpector","boards":{"daily":30,"weekly":107,"monthly":91,"daily_rate":44,"weekly_rate":88,"monthly_rate":75}},{"full_name":"NVIDIA/TensorRT-LLM","name":"TensorRT-LLM","boards":{}},{"full_name":"NVIDIA/apex","name":"apex","boards":{}},{"full_name":"NVIDIA/cosmos","name":"cosmos","boards":{}},{"full_name":"NVIDIA/cuda-samples","name":"cuda-samples","boards":{}},{"full_name":"NVIDIA/cudf","name":"cudf","boards":{}},{"full_name":"NVIDIA/cudnn-frontend","name":"cudnn-frontend","boards":{}},{"full_name":"NVIDIA/cutlass","name":"cutlass","boards":{}},{"full_name":"NVIDIA/garak","name":"garak","boards":{}},{"full_name":"NVIDIA/nvidia-docker","name":"nvidia-docker","boards":{}},{"full_name":"NVIDIA/open-gpu-kernel-modules","name":"open-gpu-kernel-modules","boards":{}}],"issues":[],"discussions":[],"latest_release":null,"readme":true,"readme_zh":false,"news":[],"stale":true,"snapshot_at":"2026-11-04T14:00:00Z","history_start":"2026-09-06"}