#streaming parts
64 related articles
·3 min
Running the 1.56TB Kimi K3 Model on 8GB RAM with Pure C
A developer built a pure C99 inference engine that runs the 1.56TB Kimi K3 model on 8GB RAM using MoE sparsity and NVMe on-demand loading—no GPU, 176KB binary.
Read more →
·3 min
Moonshot AI Open-Sources FlashKDA: A Deep Dive into High-Performance CUDA Kernels for KDA Attention
Moonshot AI open-sources FlashKDA, providing high-performance CUDA kernels for Kimi Delta Attention. Learn about its technical principles, performance gains, and value for long-context training and inference acceleration.
Read more →
·3 min
Moonshot AI Open-Sources FlashKDA: A Deep Dive into High-Performance CUDA Kernels for KDA Attention
Moonshot AI open-sources FlashKDA, providing high-performance CUDA kernels for Kimi Delta Attention. Explore its technical principles, performance gains, and value for long-context training and inference.
Read more →
·3 min
Ctrlb-decompose: Denoise Logs Before Feeding Them to LLMs — Save Tokens, Improve Quality
Ctrlb-decompose is an open-source log denoising tool that strips redundant noise via templatization and clustering before sending logs to LLMs, reducing Token costs and improving AI analysis quality.
Read more →
·3 min
Ctrlb-decompose: Denoise Logs Before Feeding Them to LLMs — Save Tokens, Improve Quality
Ctrlb-decompose is an open-source log denoising tool that strips redundant noise from logs before sending them to LLMs, reducing Token costs and improving AI analysis quality for AIOps and observability.
Read more →
·5 min
Running GPT-5.6 Inside Claude Code: Best Practices for Subagent Orchestration and System Prompts
Deep dive into running OpenAI GPT-5.6 inside Claude Code: comparing Codex vs Claude Code on subagent orchestration, workflow design, and system prompt quality, revealing how harness engineering determines model output.
Read more →
·5 min
Complete Breakdown of Core Competencies for AI Agent Engineers: From Demo to Production-Grade Systems
Deep breakdown of 4 core AI Agent engineer competencies: business decomposition, multi-Agent architecture, quantitative evaluation, and engineering delivery—bridging the gap from Demo to production.
Read more →
·3 min
After 6 Billion Tokens, Here's What I've Learned About AI Agents
A power user who consumed over 6 billion Tokens shares hard-won insights on AI Agents: the real costs, the time investment, and maintaining healthy boundaries.
Read more →
·5 min
Gemini API in Practice: Building AI Agents with 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.
Read more →
·3 min
Multi-Agent AI Paper Writing System: A Full-Stack Breakdown of FastAPI + Vue3
A deep dive into an AI paper writing system built with FastAPI + Vue3, covering multi-agent collaboration, RAG, streaming output, and full academic workflow automation.
Read more →
·6 min
Vue3 from Scratch: A Hands-On Journey to Building an AI Health Monitoring System
A Vue3 beginner tutorial centered on "learn just enough, apply immediately." A three-stage path covers reactivity, Composition API, Element Plus, and data visualization, culminating in an enterprise-grade AI health monitoring system with blood sugar management, RAG consultation, and doctor-patient collaboration.
Read more →
·3 min
LangChain v1.3 Hands-On Tutorial: Deep Dive into Agents, RAG, and Local Model Deployment
Deep dive into LangChain v1.3: compare LangChain, LangGraph, and DeepAgent paradigms, explore RAG pipelines, multi-agent systems, and local LLM deployment for enterprise AI apps.
Read more →
·2 min
3-Month Roadmap to Becoming an AI/LLM Engineer: A Systematic Learning Guide
A 3-month structured roadmap for developers transitioning into AI/LLM engineering: Python & API basics, LangChain/FastAPI stack, and RAG/Agent projects.
Read more →
·2 min
OpenAI's Five-in-One Launch: Sol, Desktop Agent, and Real-Time Translation Explained
OpenAI launches five major updates at once: flagship model Sol, balanced Terra, low-cost Luna, desktop agent ChatGPT Work, and real-time translation voice model GPT Live. Full breakdown inside.
Read more →
·3 min
DeepAgents in Practice: A Complete Guide to Building a HarmonyOS Automated Testing Agent
A deep dive into DeepAgents' core mechanisms, with a hands-on guide to building a HarmonyOS automated testing Agent — covering create_deep_agent, LangChain comparison, and long-chain task planning.
Read more →
·3 min
Build an MCP Server in 10 Minutes: Let AI Call Your Code Directly
MCP (Model Context Protocol) is the open standard for AI tool integration. Build your own MCP server with ~20 lines of Python. Learn tools, resources, prompts, and both local and remote deployment.
Read more →
·4 min
LangChain + LangGraph Full-Stack in Practice: A Production-Ready Guide to Six Core Modules and Agent Deployment
A systematic breakdown of LangChain's six core modules (Models/Prompts/Chains/Memory/RAG/Agent) and LangGraph's state graph, persistence, and HITL — with production deployment tips.
Read more →
shadcn/helpers Open-Sourced: createCha…
·2 min
shadcn/helpers Open-Sourced: createChat Makes AI Component Testing More Efficient
shadcn open-sources @shadcn/helpers with createChat — a utility for AI SDK and TanStack AI that enables scripted conversations, tool calls, and deterministic testing.
Read more →
Why Are Open Source Projects Collectiv…
·2 min
Why Are Open Source Projects Collectively Migrating to Message Scroller Components? A Deep Technical Analysis
Why are open source projects migrating to message-scroller components? We break down virtualized rendering, scroll anchoring, and dynamic heights — plus the maintenance, UX, and ecosystem logic driving the shift.
Read more →
Is Chasing the Latest AI Models Worth …
·2 min
Is Chasing the Latest AI Models Worth It? A Big Tech Engineer's Honest Question — and a Rational Answer
A 10-year big tech data engineer asks: why chase the latest AI models? This deep dive analyzes the three core motivations behind AI tool upgrades and helps you find the right model selection strategy.
Read more →