🚀 Accelerate training and inference of 🤗 Transformers and 🤗 Diffusers with easy to use hardware optimization tools

Quantized BLAS

Unify Efficient Fine-Tuning of 100+ LLMs

Faster Whisper transcription with CTranslate2

Train, Evaluate, Optimize, Deploy Computer Vision Models via OpenVINO™

This is the official PyTorch implementation of "LLM-QBench: A Benchmark Towards the Best Practice for Post-training Quantization of Large Language Models", and also an efficient LLM compression tool with various advanced compression methods, supporting multiple inference backends.

Neural Network Compression Framework for enhanced OpenVINO™ inference

🤗 Optimum Intel: Accelerate inference with Intel optimization tools

AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.

SOTA Weight-only Quantization Algorithm for LLMs. This is official implementation of "Optimize Weight Rounding via Signed Gradient Descent for the Quantization of LLMs"

SOTA low-bit LLM quantization (INT8/FP8/INT4/FP4/NF4) & sparsity; leading model compression techniques on TensorFlow, PyTorch, and ONNX Runtime

Sparsity-aware deep learning inference runtime for CPUs

Efficient computing methods developed by Huawei Noah's Ark Lab

Create and integrate custom data types, layouts and kernels with up to 2x speedups and 65% less VRAM for inference and training

模型压缩的小白入门教程

Self-Created Tools to convert ONNX files (NCHW) to TensorFlow/TFLite/Keras format (NHWC). The purpose of this tool is to solve the massive Transpose extrapolation problem in onnx-tensorflow (onnx-tf). I don't need a Star, but give me a pull request.

An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.

Dataflow compiler for QNN inference on FPGAs

Contrastive-LSH Embedding and Tokenization Technique for Multivariate Time Series Classification

Brevitas: neural network quantization in PyTorch