Run gpt-oss 120B on vLLM with an AMD Instinct MI300X GPU Droplet
‘ In this tutorial, we show how to run gpt-oss 120b on an AMD Instinct MI300X powered GPU Droplet, step by step. ‘
Simplified testing with Gradient™ AI SQL Agent Template
Learn more about the new Gradient AI Platform agent templates, and how to extend them using natural language to generate queries and mock datasets.
The Role of Warps in Parallel Processing: Optimizing GPU Performance for High-Speed Computing
This article reviews the function of warps in GPU parallel processing and explains how they enhance GPU performance for high-speed computing, efficient execution, and workload balancing to give insight into the inner workings of AI model training.
Understanding LLM Poisoning
Discover how LLM poisoning works, why even 0.01% poisoned data can compromise AI systems, and the steps to prevent backdoor attacks in models.
How to Choose the Right GPU for vLLM Inference
Size and configure GPUs for vLLM inference. Master memory requirements, KV cache, quantization, and tensor parallelism for LLM deployment.
Writing ResNet from Scratch in PyTorch
In this continuation on our series of writing DL models from scratch with PyTorch, we learn how to create, train, and evaluate a ResNet neural network for CIFAR-100 image classification.
An Overview of AI Hallucinations with RAG and Knowledge Graphs
Explore how RAG (Retrieval-Augmented Generation) and knowledge graphs tackle AI hallucinations. Understand their role in grounding AI responses with accurate, real-world information for more reliable outputs.
Optimize Production with PyTorch/TF, ONNX, TensorRT & LiteRT
Learn how to optimize and deploy AI models efficiently across PyTorch, TensorFlow, ONNX, TensorRT, and LiteRT for faster production workflows.
Building a Personal Coding Assistant in Just 6 Lines of Code
Explore the future of coding with AI-powered assistants like Code Llama, transforming how developers create, debug, and deploy software. Introduction These days many companies are using AI coding assistants to automate boilerplate code for product listings, allowing developers to work on more complex features. Recently, Devin (the world's first fully autonomous AI software engineer) was […]
Few-Shot Prompting: Techniques, Examples, and Best Practices
Learn the fundamentals of few-shot prompting in AI, with key techniques, examples, and best practices to improve model performance and accuracy.
