Applications

AI Infrastructure Applications

NVIDIA cuTile Python Tutorial: Building Tiled GPU Kernels for Vector Addition, Matrix Addition, and Matrix Multiplication in Colab
ByRicardo June 9, 2026

In this tutorial, we implement a sophisticated hands-on workflow for NVIDIA cuTile Python, a tile-based GPU programming interface for writing environment friendly CUDA-style kernels instantly in Python. We begin by making ready a Colab-friendly setting, checking the obtainable GPU, driver, CUDA, and cuTile installations earlier than working any kernel code. We then construct tiled examples…

Read More NVIDIA cuTile Python Tutorial: Building Tiled GPU Kernels for Vector Addition, Matrix Addition, and Matrix Multiplication in Colab
Applications Artificial Intelligence

Building Reflective Prompt Optimization with GEPA: Multi-Component Prompts, Structured Feedback, and Held-Out Validation
ByRicardo June 7, 2026

In this tutorial, we use GEPA as a reflective prompt-evolution framework to enhance the way in which a language mannequin solves arithmetic phrase issues. We start with a weak seed immediate, create a small deterministic benchmark, outline a structured evaluator, and move actionable suggestions to GEPA so it could possibly perceive why a candidate immediate…

Read More Building Reflective Prompt Optimization with GEPA: Multi-Component Prompts, Structured Feedback, and Held-Out Validation
AI Infrastructure Applications

How to Build a Document Intelligence Backend with iii Using Workers, Functions, and Cron Triggers
ByRicardo June 3, 2026June 3, 2026

In this tutorial, we construct a document-intelligence workflow with iii. We start by putting in the iii engine and Python SDK, then begin the engine as a background course of and join a Python employee to it. After the setup, we register separate features for textual content normalization, tokenization, sentiment evaluation, key phrase extraction, reporting,…

Read More How to Build a Document Intelligence Backend with iii Using Workers, Functions, and Cron Triggers
Applications Artificial Intelligence

How to Speed Up Transformer Training Using NVIDIA Apex (FusedAdam, FusedLayerNorm) and Native torch.amp
ByRicardo June 2, 2026

In this tutorial, we work by means of an implementation of NVIDIA Apex, specializing in the elements that also matter in fashionable GPU coaching workflows. Instead of treating Apex as a normal mixed-precision library, we separate the older elements from the still-useful ones and check them instantly. We start by checking the CUDA runtime, constructing…

Read More How to Speed Up Transformer Training Using NVIDIA Apex (FusedAdam, FusedLayerNorm) and Native torch.amp
AI Shorts Applications

Trajectory Releases a Concurrent Multi-LoRA Training Stack for Continual Learning, Reporting a 2.81× Experiment-Throughput Gain
ByRicardo May 31, 2026May 31, 2026

Trajectory’s concurrent multi-LoRA stack experiences a 2.81× experiment-throughput acquire over single-tenant RL, with all code within the NovaSky-AI/SkyRL GitHub repository. Most language fashions enhance in discontinuous jumps. A staff collects knowledge, trains, and ships a new model. This takes months and produces outstanding or catastrophic conduct for customers. Trajectory needs to switch that cycle with…

Read More Trajectory Releases a Concurrent Multi-LoRA Training Stack for Continual Learning, Reporting a 2.81× Experiment-Throughput Gain
Applications Artificial Intelligence

A Coding Guide to Implement a pgvector-Powered Semantic, Hybrid, Sparse, and Quantized Vector Search System
ByRicardo May 28, 2026

In this tutorial, we construct a full pgvector playground inside Google Colab and discover how PostgreSQL can work as a highly effective vector database for contemporary AI purposes. We begin by putting in PostgreSQL, compiling the pgvector extension, connecting via Psycopg, and registering vector varieties for clean Python integration. Then, we create embeddings with SentenceTransformers,…

Read More A Coding Guide to Implement a pgvector-Powered Semantic, Hybrid, Sparse, and Quantized Vector Search System
AI Shorts Applications

WorkOS Releases auth.md: An Open Agent Registration Protocol Built on OAuth Standards
ByRicardo May 25, 2026

For years, authentication on the online adopted one design assumption: a human sits behind a browser. Click a button. Fill out a kind. Verify an e mail. Copy an API key and paste it some place else. That mannequin doesn’t work when the consumer is delegating work to an agent. Agents are already writing code,…

Read More WorkOS Releases auth.md: An Open Agent Registration Protocol Built on OAuth Standards
Applications Artificial Intelligence

How to Build a Single-Cell RNA-seq Analysis Pipeline with Scanpy for PBMC Clustering, Annotation, and Trajectory Discovery
ByRicardo May 9, 2026May 9, 2026

In this tutorial, we carry out a sophisticated single-cell RNA-seq evaluation workflow utilizing Scanpy on the PBMC-3k benchmark dataset. We begin by loading the dataset, inspecting its construction, and making use of high quality management checks to consider gene counts, complete counts, mitochondrial content material, and ribosomal gene alerts. We then filter low-quality cells and…

Read More How to Build a Single-Cell RNA-seq Analysis Pipeline with Scanpy for PBMC Clustering, Annotation, and Trajectory Discovery
Agentic AI Applications

How to Build a Fully Interactive Multi-Page NiceGUI Application with Real-Time Dashboard, CRUD Operations, File Upload, and Async Chat
ByRicardo May 7, 2026May 7, 2026

In this tutorial, we construct a absolutely interactive, multi-page net software utilizing NiceGUI. We begin by organising the atmosphere and designing a reusable format that features navigation, theming, and darkish mode help. As we transfer ahead, we implement a reside dashboard with real-time metrics and charts, demonstrating reactive bindings and timed updates. We then lengthen…

Read More How to Build a Fully Interactive Multi-Page NiceGUI Application with Real-Time Dashboard, CRUD Operations, File Upload, and Async Chat
Agentic AI Applications

Build a Modular Skill-Based Agent System for LLMs with Dynamic Tool Routing in Python
ByRicardo May 5, 2026

In this tutorial, we construct a full skill-based agent system for giant language fashions and discover how modular capabilities will be structured like an working system for AI brokers. We outline reusable abilities, connect metadata and schemas to them, register them in a central registry, and allow dynamic orchestration by way of instrument calling and…

Read More Build a Modular Skill-Based Agent System for LLMs with Dynamic Tool Routing in Python

Applications

NVIDIA cuTile Python Tutorial: Building Tiled GPU Kernels for Vector Addition, Matrix Addition, and Matrix Multiplication in Colab

Building Reflective Prompt Optimization with GEPA: Multi-Component Prompts, Structured Feedback, and Held-Out Validation

How to Build a Document Intelligence Backend with iii Using Workers, Functions, and Cron Triggers

How to Speed Up Transformer Training Using NVIDIA Apex (FusedAdam, FusedLayerNorm) and Native torch.amp

Trajectory Releases a Concurrent Multi-LoRA Training Stack for Continual Learning, Reporting a 2.81× Experiment-Throughput Gain

A Coding Guide to Implement a pgvector-Powered Semantic, Hybrid, Sparse, and Quantized Vector Search System

WorkOS Releases auth.md: An Open Agent Registration Protocol Built on OAuth Standards

How to Build a Single-Cell RNA-seq Analysis Pipeline with Scanpy for PBMC Clustering, Annotation, and Trajectory Discovery

How to Build a Fully Interactive Multi-Page NiceGUI Application with Real-Time Dashboard, CRUD Operations, File Upload, and Async Chat

Build a Modular Skill-Based Agent System for LLMs with Dynamic Tool Routing in Python

Curated by experts. Filtered for relevance.

Resources

About

Subscribe & learn more every day!