intel / neural-compressorLinks
SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime
☆2,544Updated last week
Alternatives and similar repositories for neural-compressor
Users that are interested in neural-compressor are comparing it to the libraries listed below
Sorting:
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on H…☆3,007Updated this week
- A Python package for extending the official PyTorch that can easily obtain performance on Intel platform☆1,997Updated this week
- 🚀 Accelerate inference and training of 🤗 Transformers, Diffusers, TIMM and Sentence Transformers with easy to use hardware optimization…☆3,215Updated 2 weeks ago
- A unified library of SOTA model optimization techniques like quantization, pruning, distillation, speculative decoding, etc. It compresse…☆1,681Updated this week
- ⚡ Build your chatbot within minutes on your favorite device; offer SOTA compression techniques for LLMs; run LLMs efficiently on Intel Pl…☆2,169Updated last year
- 🤗 Optimum Intel: Accelerate inference with Intel optimization tools☆518Updated this week
- [ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models☆1,577Updated last year
- Kernl lets you run PyTorch transformer models several times faster on GPU with a single line of code, and is designed to be easily hackab…☆1,584Updated last year
- AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.☆2,521Updated this week
- PyTorch native quantization and sparsity for training and inference☆2,576Updated this week
- A pytorch quantization backend for optimum☆1,019Updated last month
- Reference implementations of MLPerf® inference benchmarks☆1,506Updated this week
- ONNX Optimizer☆780Updated last month
- A Python-level JIT compiler designed to make unmodified PyTorch programs faster.☆1,069Updated last year
- MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.☆2,083Updated 5 months ago
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆3,389Updated 5 months ago
- Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".☆2,235Updated last year
- Neural Network Compression Framework for enhanced OpenVINO™ inference☆1,111Updated this week
- PyTorch/TorchScript/FX compiler for NVIDIA GPUs using TensorRT☆2,907Updated this week
- The Torch-MLIR project aims to provide first class support from the PyTorch ecosystem to the MLIR ecosystem.☆1,700Updated this week
- Transformer related optimization, including BERT, GPT☆6,370Updated last year
- AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (N…☆4,695Updated this week
- FB (Facebook) + GEMM (General Matrix-Matrix Multiplication) - https://code.fb.com/ml-applications/fbgemm/☆1,502Updated this week
- Representation and Reference Lowering of ONNX Models in MLIR Compiler Infrastructure☆953Updated last week
- A machine learning compiler for GPUs, CPUs, and ML accelerators☆3,819Updated this week
- Automatically Discovering Fast Parallelization Strategies for Distributed Deep Neural Network Training☆1,849Updated this week
- An open-source efficient deep learning framework/compiler, written in python.☆737Updated 3 months ago
- PyTriton is a Flask/FastAPI-like interface that simplifies Triton's deployment in Python environments.☆834Updated 4 months ago
- Intel® AI Reference Models: contains Intel optimizations for running deep learning workloads on Intel® Xeon® Scalable processors and Inte…☆723Updated this week
- The Triton TensorRT-LLM Backend☆909Updated this week