microsoft / OliveLinks
Olive: Simplify ML Model Finetuning, Conversion, Quantization, and Optimization for CPUs, GPUs and NPUs.
☆2,203Updated this week
Alternatives and similar repositories for Olive
Users that are interested in Olive are comparing it to the libraries listed below
Sorting:
- Generative AI extensions for onnxruntime☆902Updated this week
- ONNX Script enables developers to naturally author ONNX functions and models using a subset of Python.☆413Updated this week
- A Python package for extending the official PyTorch that can easily obtain performance on Intel platform☆1,995Updated last week
- SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, …☆2,543Updated this week
- 🤗 Optimum Intel: Accelerate inference with Intel optimization tools☆517Updated this week
- onnxruntime-extensions: A specialized pre- and post- processing library for ONNX Runtime☆430Updated this week
- ONNXMLTools enables conversion of models to ONNX☆1,128Updated last week
- 🚀 Accelerate inference and training of 🤗 Transformers, Diffusers, TIMM and Sentence Transformers with easy to use hardware optimization…☆3,203Updated this week
- Examples for using ONNX Runtime for model training.☆358Updated last year
- A pytorch quantization backend for optimum☆1,014Updated 3 weeks ago
- ONNX Optimizer☆781Updated last month
- PyTorch native quantization and sparsity for training and inference☆2,560Updated this week
- A unified library of SOTA model optimization techniques like quantization, pruning, distillation, speculative decoding, etc. It compresse…☆1,637Updated this week
- Examples for using ONNX Runtime for machine learning inferencing.☆1,557Updated 2 weeks ago
- ⚡ Build your chatbot within minutes on your favorite device; offer SOTA compression techniques for LLMs; run LLMs efficiently on Intel Pl…☆2,170Updated last year
- Run Generative AI models with simple C++/Python API and using OpenVINO Runtime☆388Updated this week
- MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.☆2,081Updated 5 months ago
- Simple, safe way to store and distribute tensors☆3,547Updated this week
- ⚠️DirectML is in maintenance mode ⚠️ DirectML is a high-performance, hardware-accelerated DirectX 12 library for machine learning. Direct…☆2,541Updated last week
- ☆1,028Updated last year
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on H…☆2,993Updated this week
- 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…☆1,585Updated last year
- Common utilities for ONNX converters☆288Updated 3 months ago
- PyTorch/TorchScript/FX compiler for NVIDIA GPUs using TensorRT☆2,904Updated this week
- AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (N…☆4,697Updated last month
- On-device AI across mobile, embedded and edge for PyTorch☆3,678Updated this week
- Low-bit LLM inference on CPU/NPU with lookup table☆902Updated 6 months ago
- High-efficiency floating-point neural network inference operators for mobile, server, and Web☆2,196Updated this week
- PyTriton is a Flask/FastAPI-like interface that simplifies Triton's deployment in Python environments.☆834Updated 4 months ago
- cudnn_frontend provides a c++ wrapper for the cudnn backend API and samples on how to use it☆652Updated last week