microsoft / Olive
Olive: Simplify ML Model Finetuning, Conversion, Quantization, and Optimization for CPUs, GPUs and NPUs.
☆1,524Updated this week
Related projects: ⓘ
- Generative AI extensions for onnxruntime☆421Updated this week
- A Python package for extending the official PyTorch that can easily obtain performance on Intel platform☆1,554Updated this week
- SOTA low-bit LLM quantization (INT8/FP8/INT4/FP4/NF4) & sparsity; leading model compression techniques on TensorFlow, PyTorch, and ONNX R…☆2,152Updated this week
- Simple, safe way to store and distribute tensors☆2,755Updated 2 weeks ago
- Examples for using ONNX Runtime for model training.☆301Updated last month
- ☆1,014Updated 8 months ago
- 🤗 Optimum Intel: Accelerate inference with Intel optimization tools☆380Updated this week
- ONNX Script enables developers to naturally author ONNX functions and models using a subset of Python.☆270Updated this week
- Examples for using ONNX Runtime for machine learning inferencing.☆1,144Updated 2 weeks ago
- 🚀 Accelerate training and inference of 🤗 Transformers and 🤗 Diffusers with easy to use hardware optimization tools☆2,461Updated this week
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper and Ada GPUs…☆1,817Updated this week
- ⚡ Build your chatbot within minutes on your favorite device; offer SOTA compression techniques for LLMs; run LLMs efficiently on Intel Pl…☆2,106Updated 3 weeks ago
- onnxruntime-extensions: A specialized pre- and post- processing library for ONNX Runtime☆319Updated this week
- ONNXMLTools enables conversion of models to ONNX☆992Updated 3 months ago
- DirectML is a high-performance, hardware-accelerated DirectX 12 library for machine learning. DirectML provides GPU acceleration for comm…☆2,172Updated last week
- A pytorch quantization backend for optimum☆758Updated this week
- MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.☆1,843Updated last week
- AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (N…☆4,531Updated last week
- TensorRT Model Optimizer is a unified library of state-of-the-art model optimization techniques such as quantization, sparsity, distillat…☆439Updated this week
- Actively maintained ONNX Optimizer☆634Updated 6 months ago
- cudnn_frontend provides a c++ wrapper for the cudnn backend API and samples on how to use it☆422Updated 2 weeks ago
- PyTriton is a Flask/FastAPI-like interface that simplifies Triton's deployment in Python environments.☆715Updated last month
- A Python-level JIT compiler designed to make unmodified PyTorch programs faster.☆995Updated 5 months ago
- 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…☆1,522Updated 7 months ago
- Common utilities for ONNX converters☆245Updated 3 months ago
- PyTorch native quantization and sparsity for training and inference☆748Updated this week
- Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".☆1,877Updated 5 months ago
- AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:☆1,624Updated last week
- Accessible large language models via k-bit quantization for PyTorch.☆6,042Updated this week
- On-device AI across mobile, embedded and edge for PyTorch☆1,698Updated this week