{"payload":{"pageCount":2,"repositories":[{"type":"Public","name":"nm-vllm","owner":"neuralmagic","isFork":true,"description":"A high-throughput and memory-efficient inference and serving engine for LLMs","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":25,"issueCount":1,"starsCount":217,"forksCount":2851,"license":"Other","participation":[7,22,18,19,6,14,8,12,5,5,14,11,20,18,21,21,8,16,14,1,21,10,17,23,26,19,39,30,6,11,17,21,24,34,15,34,46,22,14,15,6,11,12,5,6,1,3,3,8,5,7,14],"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-06-09T00:20:57.464Z"}},{"type":"Public","name":"AutoFP8","owner":"neuralmagic","isFork":false,"description":"","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":2,"starsCount":27,"forksCount":3,"license":"Apache License 2.0","participation":[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,5,0,15,0,7,2,5],"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-06-08T17:54:54.315Z"}},{"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","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":60,"issueCount":8,"starsCount":1995,"forksCount":141,"license":"Apache License 2.0","participation":[4,6,8,4,14,7,7,2,2,1,2,1,1,6,4,2,11,5,14,6,12,6,15,11,9,4,11,8,1,0,10,13,21,14,5,20,15,11,13,6,7,8,9,10,2,11,2,8,5,9,9,4],"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-06-07T21:37:40.110Z"}},{"type":"Public","name":"compressed-tensors","owner":"neuralmagic","isFork":false,"description":"A safetensors extension to efficiently store sparse quantized tensors on disk","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":7,"issueCount":0,"starsCount":6,"forksCount":0,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-06-07T21:27:04.282Z"}},{"type":"Public","name":"upstream-llm-foundry","owner":"neuralmagic","isFork":true,"description":"LLM training code for MosaicML foundation models","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":491,"license":"Apache License 2.0","participation":[15,10,25,7,3,8,3,6,5,12,9,7,14,13,14,8,6,16,9,9,7,16,12,10,13,10,12,7,3,9,14,8,13,17,21,12,7,7,14,7,0,0,0,0,0,0,0,0,0,0,0,0],"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-06-07T20:41:57.772Z"}},{"type":"Public","name":"tensorrt-demo","owner":"neuralmagic","isFork":false,"description":"","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":1,"license":null,"participation":[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,5,1],"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-06-07T18:56:01.985Z"}},{"type":"Public","name":"lm-evaluation-harness","owner":"neuralmagic","isFork":true,"description":"A framework for few-shot evaluation of autoregressive language models.","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":4,"issueCount":0,"starsCount":2,"forksCount":1428,"license":"MIT License","participation":[27,2,28,18,3,7,7,6,8,12,3,1,0,3,4,3,18,6,2,7,19,5,5,15,5,1,8,0,0,0,0,2,26,0,0,0,0,0,0,0,0,0,0,0,2,0,0,0,0,0,0,0],"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-06-07T15:58:11.587Z"}},{"type":"Public","name":"deepsparse","owner":"neuralmagic","isFork":false,"description":"Sparsity-aware deep learning inference runtime for CPUs","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":2908,"forksCount":168,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-06-06T22:15:21.762Z"}},{"type":"Public","name":"docs","owner":"neuralmagic","isFork":false,"description":"Top-level directory for documentation and general content","allTopics":[],"primaryLanguage":{"name":"MDX","color":"#fcb32c"},"pullRequestCount":3,"issueCount":0,"starsCount":120,"forksCount":7,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-06-06T17:25:27.106Z"}},{"type":"Public","name":"guidellm","owner":"neuralmagic","isFork":false,"description":"","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":0,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-06-06T13:33:48.373Z"}},{"type":"Public","name":"nm-vllm-utils","owner":"neuralmagic","isFork":false,"description":"Various utilities for use with nm-vllm","allTopics":[],"primaryLanguage":{"name":"Makefile","color":"#427819"},"pullRequestCount":3,"issueCount":0,"starsCount":0,"forksCount":0,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-06-05T23:45:44.442Z"}},{"type":"Public","name":"transformers","owner":"neuralmagic","isFork":true,"description":"🤗Transformers: State-of-the-art Natural Language Processing for Pytorch and TensorFlow 2.0.","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":11,"issueCount":0,"starsCount":9,"forksCount":25228,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-06-05T20:10:17.128Z"}},{"type":"Public","name":"yolov5","owner":"neuralmagic","isFork":true,"description":"YOLOv5 in PyTorch > ONNX > CoreML > TFLite","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":7,"issueCount":0,"starsCount":20,"forksCount":15760,"license":"GNU General Public License v3.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-06-03T04:48:05.217Z"}},{"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.","allTopics":[],"primaryLanguage":{"name":"Jupyter Notebook","color":"#DA5B0B"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":176,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-29T15:09:33.130Z"}},{"type":"Public","name":"helm-charts","owner":"neuralmagic","isFork":false,"description":"Helm charts for deploying NM VLLM","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":1,"issueCount":0,"starsCount":3,"forksCount":0,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-21T08:08:14.828Z"}},{"type":"Public","name":"hackathon_2024","owner":"neuralmagic","isFork":false,"description":"woop wooop","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":"cutlass","owner":"neuralmagic","isFork":true,"description":"CUDA Templates for Linear Algebra Subroutines","allTopics":[],"primaryLanguage":{"name":"C++","color":"#f34b7d"},"pullRequestCount":1,"issueCount":0,"starsCount":0,"forksCount":819,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-16T18:37:19.212Z"}},{"type":"Public","name":"sparsezoo","owner":"neuralmagic","isFork":false,"description":"Neural network model repository for highly sparse and sparse-quantized models with matching sparsification recipes","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":362,"forksCount":23,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-10T18:57:00.696Z"}},{"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.","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":1,"issueCount":0,"starsCount":0,"forksCount":404,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-08T15:26:26.371Z"}},{"type":"Public","name":"nm-actions","owner":"neuralmagic","isFork":false,"description":"Neural Magic GHA","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":"examples","owner":"neuralmagic","isFork":false,"description":"Notebooks using the Neural Magic libraries 📓","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.","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.","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":25228,"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","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","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":"vllm-benchmarking","owner":"neuralmagic","isFork":false,"description":"Benchmarking Repo for vLLM","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":"","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","allTopics":[],"primaryLanguage":{"name":"Jupyter Notebook","color":"#DA5B0B"},"pullRequestCount":1,"issueCount":0,"starsCount":2,"forksCount":67,"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 ⚡","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":13518,"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","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":1,"issueCount":0,"starsCount":1,"forksCount":495,"license":"Other","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-07-31T16:17:04.615Z"}}],"repositoryCount":41,"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"}