225 related articles

Facing GPU fragmentation on edge devices, the PostSlate team used ncnn's Vulkan backend for cross-platform ML inference, achieving 10× speedup on RTX 4070 with half the model size and zero runtime installation.

GitHub Trending July 28: Microsoft's agent-governance-toolkit covers OWASP Agentic Top 10, book-to-skill gains 366 stars showing Claude Code skill ecosystem potential, plus browser-based 3D and GIS tools.

A deep dive into AI Agent Skills: understand the core concepts and technical implementation through the four key elements — SKILL.md, references, scripts, and assets — and learn how Skills differ from prompts.

A deep dive into AI Agent Skills: their core concepts, technical implementation, the four key elements (SKILL.md, references, scripts, assets), and how Skills differ from prompts.

Learn AI Agent core principles from scratch: understand how Agents differ from LLMs, their execution mechanisms, why rule design matters, and find the right learning path for your goals.

Deep analysis of FeyNoBg, an open-source background removal project with pre-trained models and training library, compared to remove.bg and rembg solutions.

A beginner's guide to AI Agents: understand core principles, how Agents differ from LLMs, their execution mechanisms, and get tailored learning path recommendations.

An in-depth analysis of ag-kit, a TypeScript-based AI Agent development toolkit covering core architecture, modular design, use cases, and tech selection advice for full-stack developers.

Deep dive into Dear ImGui's immediate mode GUI design, technical features, and use cases. Covers immediate vs retained mode, backend support, game engine integration, and ecosystem extensions.

A creator open-sourced a LoRA model replicating GTA San Andreas' RenderWare engine art style, delivering stable PS2-era visuals in complex scenes. We explore its technical features and nostalgic value.

A detailed guide on efficiently implementing Softmax on FPGAs, comparing Taylor series and Padé approximation methods for accuracy and resource trade-offs, with Python simulation and range reduction techniques.

This week's GitHub trending focuses on AI coding: Skills sets rules for Agents, Omniroute is a never-down AI gateway, Code Review Graph builds a code knowledge graph, PI is an open-source Agent toolkit, and AI Engineering from Scratch teaches from the ground up.

Spring AI 2.0 brings five core updates: mandatory upgrade to Spring Boot 4, Tools parsing moving up, a built-in Agentic mechanism, MCP switching to Streamable HTTP, and an on-demand tool Advisor.

Spring AI 2.0 brings five core updates: mandatory upgrade to Spring Boot 4, lifted Tools parsing, built-in Agentic mechanism, MCP switch to Streamable HTTP, and an on-demand tool-loading Advisor.

Google's official hands-on: how to go from idea to production fast with AI Studio and build AI Agents using the now-GA Interactions API. The core idea—Agents are just combinations of files.

Official Google hands-on: go from idea to production fast with AI Studio, and build AI Agents with the now-GA Interactions API. The core idea: an Agent is just a composition of files—Markdown plus a few scripts, no complex Python loops needed.

Hands-on test of open-source OfficeCLI: a single binary reads, edits, and generates Word/Excel/PPT. 1,000 cells rewritten in 0.37s, Chinese text supported. Covers XML internals, real failures, and AI Agent integration.

A systematic review of must-know topics for AI Application Engineer interviews: PTQ/QAT quantization, operator fusion, inference pipelines, latency/throughput analysis, and edge deployment of detection/segmentation/BEV models.

A systematic guide to must-know AI application engineer interview topics: PTQ/QAT quantization, operator fusion, inference pipelines, latency/throughput analysis, and edge deployment of detection/segmentation/BEV models.

An in-depth look at using AI LLMs to audit Cloudflare's open-source cryptographic library CIRCL, covering constant-time detection, side-channel vulnerabilities, and human-AI collaboration.