microsoft / onnxscript
ONNX Script enables developers to naturally author ONNX functions and models using a subset of Python.
☆348Updated this week
Alternatives and similar repositories for onnxscript:
Users that are interested in onnxscript are comparing it to the libraries listed below
- Common utilities for ONNX converters☆268Updated 5 months ago
- onnxruntime-extensions: A specialized pre- and post- processing library for ONNX Runtime☆380Updated this week
- ONNX Optimizer☆700Updated last week
- Accelerate PyTorch models with ONNX Runtime☆359Updated 2 months ago
- Examples for using ONNX Runtime for model training.☆333Updated 6 months ago
- The Triton backend for the ONNX Runtime.☆143Updated this week
- Scailable ONNX python tools☆97Updated 6 months ago
- A parser, editor and profiler tool for ONNX models.☆430Updated 3 months ago
- Representation and Reference Lowering of ONNX Models in MLIR Compiler Infrastructure☆850Updated this week
- Triton Model Navigator is an inference toolkit designed for optimizing and deploying Deep Learning models with a focus on NVIDIA GPUs.☆199Updated 2 weeks ago
- 🤗 Optimum Intel: Accelerate inference with Intel optimization tools☆462Updated this week
- Model compression for ONNX☆92Updated 5 months ago
- nvidia-modelopt is a unified library of state-of-the-art model optimization techniques like quantization, pruning, distillation, speculat…☆900Updated last week
- An open-source efficient deep learning framework/compiler, written in python.☆698Updated 2 months ago
- Generative AI extensions for onnxruntime☆703Updated this week
- A Fusion Code Generator for NVIDIA GPUs (commonly known as "nvFuser")☆324Updated this week
- A Python-level JIT compiler designed to make unmodified PyTorch programs faster.☆1,042Updated last year
- A code generator from ONNX to PyTorch code☆136Updated 2 years ago
- Visualize ONNX models with model-explorer☆33Updated 2 months ago
- Triton Model Analyzer is a CLI tool to help with better understanding of the compute and memory requirements of the Triton Inference Serv…☆474Updated 2 weeks ago
- Backward compatible ML compute opset inspired by HLO/MHLO☆470Updated last week
- Use safetensors with ONNX 🤗☆56Updated 2 months ago
- The Triton backend for the PyTorch TorchScript models.☆148Updated this week
- cudnn_frontend provides a c++ wrapper for the cudnn backend API and samples on how to use it☆551Updated last month
- torch::deploy (multipy for non-torch uses) is a system that lets you get around the GIL problem by running multiple Python interpreters i…☆180Updated 4 months ago
- The NVIDIA® Tools Extension SDK (NVTX) is a C-based Application Programming Interface (API) for annotating events, code ranges, and resou…☆381Updated this week
- Common source, scripts and utilities for creating Triton backends.☆320Updated this week
- A high-throughput and memory-efficient inference and serving engine for LLMs☆263Updated 6 months ago
- Fast low-bit matmul kernels in Triton☆297Updated this week
- common in-memory tensor structure☆984Updated 3 weeks ago