{"payload":{"pageCount":2,"repositories":[{"type":"Public","name":"compressed-tensors","owner":"neuralmagic","isFork":false,"description":"A safetensors extension to efficiently store sparse quantized tensors on disk","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":5,"issueCount":0,"starsCount":4,"forksCount":0,"license":"Apache License 2.0","participation":[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,11,15,26,6,4,6,4,10],"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-27T10:09:02.641Z"}},{"type":"Public","name":"sparseml","owner":"neuralmagic","isFork":false,"description":"Libraries for applying sparsification recipes to neural networks with a few lines of code, enabling faster and smaller models","topicNames":["sparsity","keras","deep-learning-algorithms","deep-learning-library","pruning","object-detection","computer-vision-algorithms","onnx","deep-learning-models","sparsification"],"topicsNotShown":9,"allTopics":["sparsity","keras","deep-learning-algorithms","deep-learning-library","pruning","object-detection","computer-vision-algorithms","onnx","deep-learning-models","sparsification","pruning-algorithms","smaller-models","sparsification-recipes","nlp","tensorflow","pytorch","image-classification","transfer-learning","automl"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":57,"issueCount":6,"starsCount":1993,"forksCount":140,"license":"Apache License 2.0","participation":[7,13,4,6,8,4,14,7,7,2,2,1,2,1,1,6,4,2,11,5,14,6,12,6,15,11,9,4,11,8,1,0,10,13,21,14,5,20,15,11,13,6,7,8,9,10,2,11,2,8,5,9],"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-27T10:03:58.415Z"}},{"type":"Public","name":"nm-vllm-utils","owner":"neuralmagic","isFork":false,"description":"Various utilities for use with nm-vllm","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Makefile","color":"#427819"},"pullRequestCount":2,"issueCount":0,"starsCount":0,"forksCount":0,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-27T09:19:39.160Z"}},{"type":"Public","name":"nm-vllm","owner":"neuralmagic","isFork":true,"description":"A high-throughput and memory-efficient inference and serving engine for LLMs","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":27,"issueCount":0,"starsCount":214,"forksCount":2709,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-27T07:51:21.439Z"}},{"type":"Public","name":"AutoFP8","owner":"neuralmagic","isFork":false,"description":"","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":1,"starsCount":15,"forksCount":3,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-24T13:10:44.927Z"}},{"type":"Public","name":"deepsparse","owner":"neuralmagic","isFork":false,"description":"Sparsity-aware deep learning inference runtime for CPUs","topicNames":["nlp","performance","computer-vision","inference","machinelearning","pruning","object-detection","pretrained-models","quantization","cpus"],"topicsNotShown":4,"allTopics":["nlp","performance","computer-vision","inference","machinelearning","pruning","object-detection","pretrained-models","quantization","cpus","onnx","sparsification","llm-inference","deepsparse"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":19,"issueCount":5,"starsCount":2899,"forksCount":168,"license":"Other","participation":[9,4,6,4,5,2,10,12,11,9,15,5,13,12,7,10,13,19,11,25,15,9,8,2,10,11,6,6,13,11,2,11,6,10,8,5,10,4,9,1,5,2,0,2,1,4,2,1,1,1,0,0],"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-21T14:45:53.166Z"}},{"type":"Public","name":"helm-charts","owner":"neuralmagic","isFork":false,"description":"Helm charts for deploying NM VLLM","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":1,"issueCount":0,"starsCount":3,"forksCount":0,"license":"Apache License 2.0","participation":[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,1,9,4,0,8,8,7,0,0],"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-21T08:08:14.828Z"}},{"type":"Public","name":"hackathon_2024","owner":"neuralmagic","isFork":false,"description":"woop wooop","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Jupyter Notebook","color":"#DA5B0B"},"pullRequestCount":4,"issueCount":0,"starsCount":0,"forksCount":0,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-21T07:46:06.879Z"}},{"type":"Public","name":"lm-evaluation-harness","owner":"neuralmagic","isFork":true,"description":"A framework for few-shot evaluation of autoregressive language models.","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":3,"issueCount":0,"starsCount":2,"forksCount":1391,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-17T22:54:40.830Z"}},{"type":"Public","name":"cutlass","owner":"neuralmagic","isFork":true,"description":"CUDA Templates for Linear Algebra Subroutines","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"C++","color":"#f34b7d"},"pullRequestCount":1,"issueCount":0,"starsCount":0,"forksCount":814,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-16T18:37:19.212Z"}},{"type":"Public","name":"docs","owner":"neuralmagic","isFork":false,"description":"Top-level directory for documentation and general content","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"MDX","color":"#fcb32c"},"pullRequestCount":3,"issueCount":0,"starsCount":120,"forksCount":7,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-15T18:49:03.106Z"}},{"type":"Public","name":"sparsezoo","owner":"neuralmagic","isFork":false,"description":"Neural network model repository for highly sparse and sparse-quantized models with matching sparsification recipes","topicNames":["nlp","computer-vision","deep-learning-algorithms","yolo","resnet","pruning","transfer-learning","pretrained-models","quantization","mobilenet"],"topicsNotShown":6,"allTopics":["nlp","computer-vision","deep-learning-algorithms","yolo","resnet","pruning","transfer-learning","pretrained-models","quantization","mobilenet","deep-learning-models","object-detection-model","sparsification-recipe","smaller-models","sparse-quantized-models","models-optimized"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":6,"issueCount":1,"starsCount":361,"forksCount":23,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-10T18:57:00.696Z"}},{"type":"Public","name":"alpaca_eval","owner":"neuralmagic","isFork":true,"description":"An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Jupyter Notebook","color":"#DA5B0B"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":172,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-08T16:54:47.130Z"}},{"type":"Public","name":"nm-AutoGPTQ","owner":"neuralmagic","isFork":true,"description":"An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":1,"issueCount":0,"starsCount":0,"forksCount":396,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-08T15:26:26.371Z"}},{"type":"Public","name":"upstream-llm-foundry","owner":"neuralmagic","isFork":true,"description":"LLM training code for MosaicML foundation models","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":488,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-08T05:14:19.772Z"}},{"type":"Public","name":"nm-actions","owner":"neuralmagic","isFork":false,"description":"Neural Magic GHA","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":null,"pullRequestCount":1,"issueCount":0,"starsCount":0,"forksCount":0,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-07T14:27:13.017Z"}},{"type":"Public","name":"yolov5","owner":"neuralmagic","isFork":true,"description":"YOLOv5 in PyTorch > ONNX > CoreML > TFLite","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":7,"issueCount":0,"starsCount":20,"forksCount":15695,"license":"GNU General Public License v3.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-02T00:15:51.953Z"}},{"type":"Public","name":"examples","owner":"neuralmagic","isFork":false,"description":"Notebooks using the Neural Magic libraries 📓","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Jupyter Notebook","color":"#DA5B0B"},"pullRequestCount":1,"issueCount":0,"starsCount":38,"forksCount":6,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-04-11T20:18:29.639Z"}},{"type":"Public","name":"sparsify","owner":"neuralmagic","isFork":false,"description":"ML model optimization product to accelerate inference.","topicNames":["computer-vision","tensorflow","keras","pytorch","image-classification","pruning","object-detection","quantization","automl","onnx"],"topicsNotShown":5,"allTopics":["computer-vision","tensorflow","keras","pytorch","image-classification","pruning","object-detection","quantization","automl","onnx","deep-learning-accelerator","inference-performance","sparsification-recipe","smaller-models","sparsify"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":8,"issueCount":0,"starsCount":315,"forksCount":27,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-04-10T17:10:29.504Z"}},{"type":"Public","name":"upstream-transformers","owner":"neuralmagic","isFork":true,"description":"🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":25079,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-03-28T13:27:30.976Z"}},{"type":"Public","name":"upstream-composer","owner":"neuralmagic","isFork":true,"description":"Supercharge Your Model Training","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":400,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-03-28T13:25:33.601Z"}},{"type":"Public","name":"nm-docker","owner":"neuralmagic","isFork":false,"description":"Neural Magic Docker","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Dockerfile","color":"#384d54"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":0,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-03-19T17:43:39.354Z"}},{"type":"Public","name":"transformers","owner":"neuralmagic","isFork":true,"description":"🤗Transformers: State-of-the-art Natural Language Processing for Pytorch and TensorFlow 2.0.","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":10,"issueCount":0,"starsCount":9,"forksCount":25079,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-03-15T02:31:32.887Z"}},{"type":"Public","name":"vllm-benchmarking","owner":"neuralmagic","isFork":false,"description":"Benchmarking Repo for vLLM","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Jupyter Notebook","color":"#DA5B0B"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":0,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-02-07T23:58:51.330Z"}},{"type":"Public","name":"optimum-deepsparse","owner":"neuralmagic","isFork":false,"description":"","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":1,"issueCount":1,"starsCount":4,"forksCount":0,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-01-15T19:23:25.676Z"}},{"type":"Public","name":"CLIP_benchmark","owner":"neuralmagic","isFork":true,"description":"CLIP-like model evaluation","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Jupyter Notebook","color":"#DA5B0B"},"pullRequestCount":1,"issueCount":0,"starsCount":2,"forksCount":65,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-12-05T16:30:46.871Z"}},{"type":"Public","name":"langchain","owner":"neuralmagic","isFork":true,"description":"⚡ Building applications with LLMs through composability ⚡","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":13317,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-12-04T11:00:39.477Z"}},{"type":"Public","name":"inference","owner":"neuralmagic","isFork":true,"description":"Reference implementations of MLPerf™ inference benchmarks","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":1,"issueCount":0,"starsCount":1,"forksCount":494,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-07-31T16:17:04.615Z"}},{"type":"Public","name":"deepsparse-digitalocean-image","owner":"neuralmagic","isFork":false,"description":"Repo for building and packaging a 1-click app for DigitalOcean","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Shell","color":"#89e051"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":0,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-07-13T20:18:10.533Z"}},{"type":"Public archive","name":"to-be-removed-llm-foundry","owner":"neuralmagic","isFork":true,"description":"LLM training code for MosaicML foundation models","topicNames":[],"topicsNotShown":0,"allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":488,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-07-13T11:45:02.580Z"}}],"repositoryCount":39,"userInfo":null,"searchable":true,"definitions":[],"typeFilters":[{"id":"all","text":"All"},{"id":"public","text":"Public"},{"id":"source","text":"Sources"},{"id":"fork","text":"Forks"},{"id":"archived","text":"Archived"},{"id":"template","text":"Templates"}],"compactMode":false},"title":"Repositories"}