PyTorch native quantization and sparsity for training and inference

VeriSilicon Tensor Interface Module

先进编译实验室的个人主页

Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels

torch_musa is an open source repository based on PyTorch, which can make full use of the super computing power of MooreThreads graphics cards.

Hands-on Notes Using OpenClaw on the MT AIBOOK

《Pytorch实用教程》（第二版）无论是零基础入门，还是CV、NLP、LLM项目应用，或是进阶工程化部署落地，在这里都有。相信在本书的帮助下，读者将能够轻松掌握 PyTorch 的使用，成为一名优秀的深度学习工程师。

a static analytical model for LLM distributed training

Flash Attention in ~100 lines of CUDA (forward pass only)

PaddlePaddle High Performance Deep Learning Inference Engine for Mobile and Edge (飞桨高性能深度学习端侧推理引擎）

library to read/write .npy and .npz files in C/C++

how to optimize some algorithm in cuda.

On-device AI across mobile, embedded and edge for PyTorch

Python package built to ease deep learning on graph, on top of existing DL frameworks.

common in-memory tensor structure

Universal LLM Deployment Engine with ML Compilation

Kaldi-compatible online fbank extractor without external dependencies

compiler learning resources collect.

Open source AUTOSAR classic platform forked from the Arctic Core

My sample code for linux

High-performance inference framework for large language models, focusing on efficiency, flexibility, and availability.

Open Machine Learning Compiler Framework

这是一个faster-rcnn的pytorch实现的库，可以利用voc数据集格式的数据进行训练。

Regrouping all neural networks for Kalray Neural Networks applications

A unified library of SOTA model optimization techniques like quantization, pruning, distillation, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks …

OpenVX sample implementation

Khronos OpenVX Tutorial Material

ppocrv5(det, cls, rec) onnx/axmodel inference pipeline

A tool to modify ONNX models in a visualization fashion, based on Netron and Flask.

A UDP/TCP Assistant. 网络调试助手