Microsoft Linear Algebra Subroutines

Generative AI extensions for onnxruntime

Source code examples from the Parallel Forall Blog

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

A JIT assembler for x86/x64 architectures supporting FPU, MMX, SSE (1-4), AVX (1-2, 512), APX, and AVX10.2

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

The Torch-MLIR project aims to provide first class support from the PyTorch ecosystem to the MLIR ecosystem.

A retargetable MLIR-based machine learning compiler and runtime toolkit.

Cross-platform, customizable ML solutions for live and streaming media.

ncnn is a high-performance neural network inference framework optimized for the mobile platform

MNN is a blazing fast, lightweight deep learning framework, battle-tested by business-critical use cases in Alibaba. Full multimodal LLM Android App:[MNN-LLM-Android](./apps/Android/MnnLlmChat/READ…

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

Quantized Neural Network PACKage - mobile-optimized implementation of quantized neural network operators

FB (Facebook) + GEMM (General Matrix-Matrix Multiplication) - https://code.fb.com/ml-applications/fbgemm/

Low-precision matrix multiplication

State-of-the-Art Deep Learning scripts organized by models - easy to train and deploy with reproducible accuracy and performance on enterprise-grade infrastructure.

[ARCHIVED] Cooperative primitives for CUDA C++. See https://github.com/NVIDIA/cccl

Tensors and Dynamic neural networks in Python with strong GPU acceleration

Optimized primitives for collective multi-GPU communication

NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.

nGraph has moved to OpenVINO

[ARCHIVED] The C++ parallel algorithms library. See https://github.com/NVIDIA/cccl

A natural language modeling framework based on PyTorch

oneAPI Deep Neural Network Library (oneDNN)

TensorFlow code and pre-trained models for BERT

Convert TensorFlow, Keras, Tensorflow.js and Tflite models to ONNX

An Open Source Machine Learning Framework for Everyone

Code samples for my book "Neural Networks and Deep Learning"

Open standard for machine learning interoperability