First Model Compression Cards

compression/aimet.yaml

@@ -0,0 +1,27 @@
+aimet:
+
+  name: "AIMET"
+
+  image_url: https://www.pillar.vc/wp-content/uploads/2021/11/Dark-blue-1600x522.png
+
+  tags: 
+    - Pruning
+    - Tensorization
+    - Quantization
+    - PyTorch
+    - TensorFlow
+    - ONNX
+    - Open-Source
+
+  url: https://github.com/quic/aimet
+
+  description: "AIMET is a library that provides advanced model quantization and compression techniques for
+  trained neural network models. It provides features that have been proven to improve run-time performance of deep learning
+  neural network models with lower compute and memory requirements and minimal impact to task accuracy."
+
+  features:
+    - "Batch-Norm Folding"
+    - "Cross-Layer Equalization"
+    - "AdaRound"
+    - "Channel Pruning"
+    - "Singular Vector Decomposition"

compression/bigdl.yaml

@@ -0,0 +1,23 @@
+bigdl:
+
+  name: "BigDL"
+
+  # URL of relevant image (e.g. logo)
+  image_url: https://www.intel.com/content/dam/www/central-libraries/us/en/images/2022-09/bigdl-logo-dark-rwd.png
+
+  tags: 
+    - Intel
+    - PyTorch
+    - Open-Source
+
+  url: https://github.com/intel/neural-compressor
+
+  description: "BigDL is a set of toolkits developed by Intel to seamlessly scales data analytics & AI applications to be run easily on both laptops to cloud infrastructures.
+  The project introduces the following set of libraries:
+      (LLM)[https://github.com/intel-analytics/BigDL/tree/main/python/llm]: Low-bit (INT3/INT4/INT5/INT8) large language model library for Intel CPU/GPU
+      (Orca)[https://bigdl.readthedocs.io/en/latest/doc/Orca/index.html]: Distributed Big Data & AI (TF & PyTorch) Pipeline on Spark and  Ray
+      (Nano)[https://bigdl.readthedocs.io/en/latest/doc/Nano/index.html]: Transparent Acceleration of Tensorflow & PyTorch Programs on Intel CPU/GPU
+      (DLlib)[https://bigdl.readthedocs.io/en/latest/doc/DLlib/index.html]: “Equivalent of Spark MLlib” for Deep Learning
+      (Chronos)[https://bigdl.readthedocs.io/en/latest/doc/Chronos/index.html]: Scalable Time Series Analysis using AutoML
+      (Friesian)[https://bigdl.readthedocs.io/en/latest/doc/Friesian/index.html]: End-to-End Recommendation Systems
+      (PPML)[https://bigdl.readthedocs.io/en/latest/doc/PPML/index.html]: Secure Big Data and AI (with SGX Hardware Security)"

compression/modelcompressiontoolkit.yaml

@@ -0,0 +1,22 @@
+modelcompressiontoolkit.yaml:
+
+  name: "Model Compression Toolkit"
+
+  image_url: https://avatars.githubusercontent.com/u/8435219?s=48&v=4
+
+  tags: 
+    - Quantization
+    - SONY
+    - Open-Source
+
+  url: https://github.com/sony/model_optimization
+
+  description: "SONY’s Model Compression Toolkit is a model compression tool that focuses on quantization
+  and comes with a suite of features that make it easier to optimise neural networks for efficient deployment,
+  including synthetic image data generation and visualisation tools."
+
+  features:
+    - "Synthetic Image Data Generation"
+    - "Power-of-Two Quantization"
+    - "Symmetric Quantization"
+    - "Enhanced Post Training Quantization"

compression/neuralcompressor.yaml

@@ -0,0 +1,29 @@
+neuralcompressor:
+
+  name: "Neural Compressor"
+
+  # URL of relevant image (e.g. logo)
+  image_url: https://avatars.githubusercontent.com/u/17888862?s=48&v=4
+
+  tags: 
+    - Pruning
+    - Distillation
+    - Quantization
+    - PyTorch
+    - TensorFlow
+    - ONNX
+    - MxNet
+    - Open-Source
+
+  url: https://github.com/intel/neural-compressor
+
+  description: "Intel® Neural Compressor aims to provide popular model compression techniques such
+  as quantization, pruning (sparsity), distillation, and neural architecture search on mainstream frameworks
+  such as TensorFlow, PyTorch, ONNX Runtime, and MXNet, as well as Intel extensions such as Intel Extension
+  for TensorFlow and Intel Extension for PyTorch."
+
+  features:
+    - "Unified scikit-learn-like API"
+    - "Accuracy Aware Tuning"
+    - "AWQ"
+    - "GPTQ"

compression/neuralnetworkintelligence.yaml

@@ -0,0 +1,25 @@
+neuralnetworkintelligence:
+
+  name: "Neural Network Intelligence"
+
+  image_url: https://github.com/microsoft/nni/raw/master/docs/img/nni_logo.png
+
+  tags: 
+    - Pruning
+    - Quantization
+    - Microsoft
+    - Open-Source
+
+  url: https://github.com/quic/aimet
+
+  description: "NNI automates feature engineering, neural architecture search, hyperparameter tuning,
+  and model compression for deep learning."
+
+  features:
+    - "DoReFa Quantization"
+    - "BNN Quantization"
+    - "LSQ Quantization"
+    - "Ln Norm Pruning"
+    - "Slim Pruning"
+    - "FPGM Pruning"
+    - "AGP Pruning"

compression/sparseml.yaml

@@ -0,0 +1,27 @@
+sparseml:
+
+  name: "SparseML"
+
+  image_url: https://www.pillar.vc/wp-content/uploads/2021/11/Dark-blue-1600x522.png
+
+  tags: 
+    - Pruning
+    - Distillation
+    - Quantization
+    - PyTorch
+    - TensorFlow
+    - Keras
+    - Open-Source
+
+  url: https://docs.neuralmagic.com/sparseml/
+
+  description: "SparseML is an open source library developed and maintained by (Neural Magic)[https://neuralmagic.com/] for applying compression recipes to neural networks.
+  Currently, it supports pruning, quantization and knowledge distillation for compressing Vision, NLP, and now, large language models as well.
+  SparseML also provides pre-compressed and pre-quantized models in their SparseZoo."
+
+  features:
+    - "Gradual Magnitude Pruning (GMP)"
+    - "Alternating Compressed/DeCompressed Pruning (AC/DC)"
+    - "Optimal BERT Surgeon (oBERT)"
+    - "Pre-Compressed models via SparseZoo"
+    - "Knowledge Distillation Recipes"

compression/tensorly.yaml

@@ -0,0 +1,26 @@
+tensorly:
+
+  name: "TensorLy"
+
+  image_url: http://tensorly.org/stable/_static/tensorly-logo.png
+
+  tags: 
+    - Tensorization
+    - PyTorch
+    - NumPy
+    - TensorFlow
+    - MxNet
+    - CuPy
+    - Jax
+    - Open-Source
+
+  url: https://github.com/intel/neural-compressor
+
+  description: "TensorLy is a Python library that aims at making tensor learning simple and accessible. It allows simple performing of tensor decomposition,
+  tensor learning and tensor algebra. Its backend system allows to seamlessly perform computation with NumPy,
+  PyTorch, JAX, MXNet, TensorFlow or CuPy, and run methods at scale on CPU or GPU."
+
+  features:
+    - "Tucker Decomposition"
+    - "Canonical Polyadic Decomposition"
+    - "Tensor Train Decomposition"