Introduction A few years ago, when I was tasked with an in-house PoC for image classification, I took sample code for ...

你是否在PyTorch模型部署中遇到过性能瓶颈？当Python实现的算子无法满足实时性要求时，自定义C++扩展和CUDA算子成为突破性能极限的关键技术。本文将系统讲解如何构建跨Python版本的C++扩展 ...

In this tutorial, we implement an advanced, practical implementation of the NVIDIA Transformer Engine in Python, focusing on how mixed-precision acceleration can be explored in a realistic deep ...

Registration is open for the RCS Spring 2026 Tutorials. Please also be aware that we have lots of recordings and slides available from past tutorials by RCS staff and vendors. For hands-on sessions ...

PyTorchで作成したモデルをONNX形式に変換する方法を実際に手を動かして理解する。 対象 PyTorchでモデルを訓練したことがある人 モデルをデプロイしたい人 「ONNXに変換したいけど、やり方が ...

As machine learning models continue to scale, a specialized, co-designed hardware and software stack is no longer optional, it’s critical. Ironwood, our latest generation Tensor Processing Unit (TPU), ...

半结构化稀疏（Semi-structured Sparsity）是一种模型优化技术，通过特定模式减少神经网络中的参数数量，在保持模型精度的同时提升推理速度和降低内存占用。其中2:4稀疏模式（每4个元素中保留2 ...

Imagine private, on‑device AI assistants and voice interfaces that run without needing cloud connectivity and respond with minimal latency, chatbots that suggest replies as you type, gaming ...

In this tutorial, we explore advanced computer vision techniques using TorchVision’s v2 transforms, modern augmentation strategies, and powerful training enhancements. We walk through the process of ...

What if you could take a innovative language model like GPT-OSS and tailor it to your unique needs, all without needing a supercomputer or a PhD in machine learning? Fine-tuning large language models ...