Avatar 🍥

KnightLi Blog

记录并分享日常

  1. Home
  2. About
  3. Archives
  4. Search
  5. Links
    1. Dark Mode

Archives

2026 507
2025 23
2024 5
2023 9
2022 33
2021 5
2020 8

Categories

AI Tools Technical Docs Hardware Development Tools AI Industry Operations Security Updates Business Analysis

Tags

AI Agent AI Tools AI Coding Codex Developer Tools Claude Code Local LLM Openai MCP Linux Claude Python Anthropic Ubuntu ChatGPT Open Source Ollama Llama.cpp NAS Gemini Prompts AI Art Game Development Godot LLM AI Models GPU Windows Cybersecurity DeepSeek
Hardware

How Intel's ATX 3.0 Design Guide Classifies PCIe Auxiliary Power Connectors for GPUs

Based on Intel's ATX 3.0 Multi Rail Desktop Platform Power Supply Design Guide, this article sorts out the roles, power ranges, and sideband signals of the common PCIe GPU auxiliary power connectors: 2x3, 2x4, and 12V-2x6.

2026-04-23
7 minute read
中文简体 中文繁體 日本語 Español
AI Tools

How to Choose Common Embedding Models: OpenAI vs BGE vs E5 vs GTE vs Jina

A practical comparison of common embedding models such as OpenAI, BGE, E5, GTE, and Jina, with a focus on how to choose for Chinese-language use cases.

2026-04-23
7 minute read
中文简体 中文繁體 日本語 Español
AI Tools

What image vectorization is: from pixel images to searchable, analyzable vector representations

A practical explanation of image vectorization: why images need to move from pixel representations to vector representations, how that process usually works, and what problems it actually solves in search, recommendation, recognition, and enterprise digital workflows.

2026-04-23
8 minute read
中文简体 中文繁體 日本語 Español
Technical Docs

What auto-editor does: cut silence automatically and export to Premiere or Resolve

A practical overview of what auto-editor is good at: making a first-pass rough cut by removing silence or low-motion sections automatically, then exporting to editors like Premiere, DaVinci Resolve, or Final Cut Pro, or rendering directly.

2026-04-23
6 minute read
中文简体 中文繁體 日本語 Español
AI Tools

AI Terms Explained: Agent, MCP, RAG, and Token in Plain Language

A plain-language guide to 10 common AI terms, including Agent, Skills, MCP, API, RAG, AIGC, and Token, to help beginners build a basic framework for understanding everyday AI discussions.

2026-04-23
6 minute read
中文简体 中文繁體 日本語 Español
AI Tools

How to Tune llama.cpp on 8GB VRAM: Why 32K Is Safer and 64K Needs KV Cache Quantization

A practical guide to tuning llama.cpp on 8GB VRAM: what 32K, 64K, and KV Cache mean, why 32K is often the safer balance point, why 64K depends more on cache quantization, and why blindly increasing CPU threads can make performance worse.

2026-04-23
7 minute read
中文简体 中文繁體 日本語 Español
Hardware

How to Check Whether a Tesla V100 Has ECC Errors

Use nvidia-smi to quickly inspect the ECC status of a Tesla V100 and determine which error counters should be 0 or N/A.

2026-04-23
2 minute read
中文简体 中文繁體 日本語 Español
Hardware

Is Tesla V100 Still Worth Buying: ECC Checks, Cooling Mods, and DIY Pitfalls

A practical guide to buying a Tesla V100: how to read production dates and visual clues, how to interpret ECC values, what signs suggest the card has been tampered with, and why DIY cooling and power setups fail so easily.

2026-04-23
9 minute read
中文简体 中文繁體 日本語 Español
AI Tools

Claude Code CLAUDE.md Guide: Rules, Memory, Hooks, and Project Setup Explained

Learn how CLAUDE.md, rules, memory, and hooks work in Claude Code, when to use each one, and how to structure a practical project-level setup.

2026-04-23
11 minute read
中文简体 中文繁體 日本語 Español
AI Tools

llama.cpp GPU Benchmark: CUDA vs ROCm vs Vulkan Scoreboard and pp512/tg128 Explained

Compare llama.cpp GPU benchmark results across CUDA, ROCm, and Vulkan, with scoreboards and plain-English explanations of pp512, tg128, Q4_0, and FA metrics.

2026-04-23
28 minute read
中文简体 中文繁體 日本語 Español
AI Tools

What the Common GPU Inference Benchmark Metrics Actually Mean: FA, pp512, tg128, and Q4_0

When reading GPU inference benchmarks, you often run into metrics like FA, pp512, tg128, Q4_0, and t/s. They all relate to performance, but they do not measure the same thing. This article breaks down what each of them actually means.

2026-04-23
8 minute read
中文简体 中文繁體 日本語 Español
Development Tools

How to Choose an Embedded Development Environment in 2026: Keil, STM32CubeIDE, VS Code, and AI Collaboration

In 2026, when AI-assisted coding has become common, how should embedded developers choose their environment? Instead of betting on a single IDE, a more practical answer is often to let Keil handle build and debugging while VS Code handles editing and AI collaboration.

2026-04-22
7 minute read
中文简体 中文繁體 日本語 Español
AI Tools

A Practical Guide to Common Tensor Formats in LLMs: FP32, FP16, BF16, TF32, and FP8

A practical introduction to the most common tensor formats used in large models: FP32, FP16, BF16, TF32, and FP8, including their bit layouts, trade-offs, and why they shape training and deployment behavior.

2026-04-22
7 minute read
中文简体 中文繁體 日本語 Español
Development Tools

How to Choose Among 8 Common Config File Formats: From INI, XML, JSON, YAML, TOML to Markdown

A practical comparison of 8 common config file formats, including INI, XML, JSON, YAML, TOML, Apache-style config, Protocol Buffers, and Markdown as it becomes newly relevant in the AI Agent era.

2026-04-22
10 minute read
中文简体 中文繁體 日本語 Español
AI Tools

A 16GB GPU Can Still Run 35B Models: VRAM Compression Strategies for MoE Models in LM Studio

A practical look at how a 16GB GPU can still run 35B-class MoE models: with the right architecture choice and LM Studio settings, 16GB VRAM does not necessarily cap you at 12B to 14B models.

2026-04-22
6 minute read
中文简体 中文繁體 日本語 Español
AI Tools

Claude Code Subagents vs Agent Teams: Differences, Use Cases, and Setup Guide

Understand when to use Claude Code Subagents, when Agent Teams make sense, and how to choose the right multi-agent workflow for coding tasks.

2026-04-22
8 minute read
中文简体 中文繁體 日本語 Español
AI Tools

GPT Image 2 Officially Launches: From Generating Images to Commercial Use

A summary of the most important capability shifts after the launch of GPT Image 2, including text rendering, photorealism, world knowledge, UI screenshot generation, and localized editing, along with how to use it in ChatGPT and the API plus prompt references for several common image-generation scenarios.

2026-04-22
9 minute read
中文简体 中文繁體 日本語 Español
AI Tools

nuwa-skill: Turning "distilling a person" from an idea into an executable workflow

alchaincyf/nuwa-skill is not just about imitating a famous person's tone. It turns the process of researching, extracting, and validating how someone thinks into a reusable Claude Code Skill.

2026-04-22
6 minute read
中文简体 中文繁體 日本語 Español
AI Tools

OpenAI Introduces ChatGPT Images 2.0: Image Generation Starts Moving Toward Deliverable Output

Based on OpenAI's ChatGPT Images 2.0 announcement on April 21, 2026, this article highlights the most important signals from the release: stronger text and layout control, better multilingual performance, broader stylistic coverage, and a shift from image generation as output to image generation as deliverable work.

2026-04-22
5 minute read
中文简体 中文繁體 日本語 Español
Hardware

12V-2x6 vs. 12VHPWR: Notes on GPU 16-Pin Power Connector Differences

A concise note on the main differences between the 12V-2x6 and 12VHPWR GPU 16-pin power connectors: cable compatibility, pin length, SENSE logic, H++ marking, and 600W output capability.

2026-04-19
4 minute read
中文简体 中文繁體 日本語 Español
AI Tools

Karpathy's 65-Line CLAUDE.md: Helping AI Coding Avoid Three Common Mistakes

A summary of Karpathy's observations on AI coding, and how Forrest Cheung turned those problems into CLAUDE.md rules: think first, keep it simple, make precise changes, and work toward verifiable goals.

2026-04-19
6 minute read
中文简体 中文繁體 日本語 Español
Hardware

Core Ultra 9 285T ES Notes: Q4A7, a B860 Engineering Board, and the 35W Power Wall

Notes on the Core Ultra 9 285T ES sample Q4A7: platform, motherboard, power delivery, memory, performance, gaming results, and buying advice. The specs look tempting, but the 35W power wall, high DDR5 latency, scarce ES boards, and limited BIOS make it better suited to low-power tinkering than a gaming PC.

2026-04-19
9 minute read
中文简体 中文繁體 日本語 Español
AI Tools

Claude Code Usage Limits Guide: Reduce Context, Use /compact, and Save Quota

Learn why Claude Code usage can run out quickly and how model choice, long context, cache misses, MCP, CLAUDE.md, /compact, /clear, /context, and /status affect quota.

2026-04-19
8 minute read
中文简体 中文繁體 日本語 Español
AI Tools

rembg Project Notes: A Local Background Removal Tool

A practical look at danielgatis/rembg: what it is, how to install it, CLI usage, Python integration, HTTP server mode, Docker usage, model choices, and where it fits in local background removal workflows.

2026-04-19
7 minute read
中文简体 中文繁體 日本語 Español
AI Tools

Ollama Multi-GPU Guide: VRAM Pooling, GPU Selection, and Performance Limits

A practical Ollama multi-GPU guide covering VRAM pooling myths, GPU selection with CUDA_VISIBLE_DEVICES and ROCR_VISIBLE_DEVICES, mixed GPU setups, Docker, PCIe, and performance limits.

2026-04-19
9 minute read
中文简体 中文繁體 日本語 Español
Hardware

Lenovo HR630x / HR650x Notes: LGA3647, 8259CL, Optane, and Common Pitfalls

Based on HR630x build logs and HR650x troubleshooting notes, this post summarizes buying and setup considerations for Lenovo HR630x / HR650x LGA3647 server barebones: CPU and Optane pairing, VRM unlocks, fan control, risers, backplanes, and BMC/UEFI notes.

2026-04-18
11 minute read
中文简体 中文繁體 日本語 Español
Hardware

MCP2221A-I/ST Selection Notes: A Handy USB-to-I2C/UART Bridge Chip

A quick look at the key parameters and practical notes for Microchip MCP2221A-I/ST: USB 2.0 to I2C/UART, GPIO multiplexing, supply range, package, speed limits, and why it belongs in a hardware debugging toolkit.

2026-04-18
6 minute read
中文简体 中文繁體 日本語 Español
Hardware

LGA3647 high TDC OEM CPU lighting idea: modify the ICC_MAX of VRM

Compiled the thoughts on the VRM ICC_MAX modification of the high TDC OEM Xeon processor on the LGA3647 platform in the ServeTheHome forum: why the machine does not turn on, what needs to be prepared, specific motherboard wiring, flash commands, BIOS modifications and risk precautions.

2026-04-18
18 minute read
中文简体 中文繁體 日本語 Español
AI Tools

Google App for Desktop: Bringing AI Search to Windows

A practical introduction to Google app for desktop: supported devices, Alt + Space shortcut, AI Mode, Google Lens, screen sharing, file uploads, local file search, and Google Drive search.

2026-04-18
7 minute read
中文简体 中文繁體 日本語 Español
Operations

Understanding the nftables Framework: Tables, Chains, Rules, and Sets

A concept-level overview of the nftables framework: what table, family, chain, rule, set, map, and verdict map are for, and how they work together to form maintainable firewall rules.

2026-04-18
5 minute read
中文简体 中文繁體 日本語 Español
Operations

nftables Quick Start: Tables, Chains, Rules, and Common Operations

A practical nftables quick start: understand table, chain, and rule, then use common commands for IP, MAC, port matching, traffic counters, rate limiting, and rule cleanup.

2026-04-18
4 minute read
中文简体 中文繁體 日本語 Español
AI Tools

Gemma 4 E4B Uncensored vs Official: Safety, Behavior, License, and Local Use

Compare the unofficial Gemma 4 E4B Uncensored derivative with Google's official Gemma 4 E4B-it model, including behavior changes, safety trade-offs, license considerations, and local deployment risks.

2026-04-18
4 minute read
中文简体 中文繁體 日本語 Español
AI Tools

Hermes Agent on Windows: WSL2, Ollama, Local Models, and Telegram Setup

A practical Hermes Agent Windows setup guide using WSL2, Ubuntu, Ollama, local models, and Telegram integration, with a simple path for running a local AI agent on a PC.

2026-04-18
4 minute read
中文简体 中文繁體 日本語 Español
AI Tools

llama-cli -hf Cache Path: Where Hugging Face GGUF Models Are Saved

A quick llama-cli -hf cache path guide explaining where Hugging Face GGUF models are saved by default and how to change the directory with LLAMA_CACHE, HF_HUB_CACHE, HUGGINGFACE_HUB_CACHE, or HF_HOME.

2026-04-17
2 minute read
中文简体 中文繁體 日本語 Español
AI Tools

How to Fix SSL Certificate Verification Failed When llama-cli Downloads from Hugging Face on Windows

Common causes and fixes when llama-cli fails SSL certificate verification while downloading Hugging Face models with -hf on Windows.

2026-04-17
2 minute read
中文简体 中文繁體 日本語 Español
Hardware

CRPS Common Redundant Server Power Supply Standard, Pin Functions, and Common Models

A practical overview of CRPS / M-CRPS common redundant server power supplies, including the 2x25 edge connector pinout, PSON/12VSB/PMBus signal functions, and common CRPS PSU models.

2026-04-17
11 minute read
中文简体 中文繁體 日本語 Español
Hardware

CSPS Common Slot Server Power Supply Interface and Pinout

A practical overview of CSPS / Common Slot server power supplies, including the 64 pin edge connector pinout, 12V output enable method, PMBus/SMBus signals, and breakout board design notes.

2026-04-16
18 minute read
中文简体 中文繁體 日本語 Español
AI Tools

codex-quota Practical Guide: Local, Web, and Docker Usage with Original CLI Commands

`codex-quota` is a lightweight tool to check ChatGPT Codex quota usage, covering local CLI, web service, and Docker/Compose usage.

2026-04-16
3 minute read
中文简体 中文繁體 日本語 Español
AI Tools

Using Claude in VS Code: From API Setup to Page Generation

A practical introduction to using Claude-like models inside VS Code for AI coding, covering plugin setup, API configuration, iterative page generation, and the boundaries that matter most in real use.

2026-04-16
5 minute read
中文简体 中文繁體 日本語 Español
Development Tools

Build Docker Images in VS Code on Windows: From Setup to Build

A practical guide to building Docker images in VS Code on Windows, including prerequisites, Dockerfile setup, build methods, and quick troubleshooting.

2026-04-16
2 minute read
中文简体 中文繁體 日本語 Español
AI Tools

Claude Identity Verification Guide: Requirements, Accepted IDs, Persona, and Failed Checks

A practical Claude identity verification guide explaining why Anthropic may ask for verification, which IDs are accepted, how Persona is involved, how data is handled, and what to do if verification fails.

2026-04-16
6 minute read
中文简体 中文繁體 日本語 Español
AI Tools

Codex Usage Limits Explained: 5-Hour Quota, Weekly Limits, and Credits

Understand how Codex 5-hour quota, weekly limits, and credits work together, why usage can drop in multiple windows, and what affects local and cloud task consumption.

2026-04-15
5 minute read
中文简体 中文繁體 日本語 Español
Hardware

A Practical Guide to Common U.2 Enterprise SSD Series

A practical overview of common U.2 enterprise SSD series from Solidigm, Samsung, Western Digital, Micron, and Kioxia, with a focus on product positioning and typical use cases.

2026-04-15
7 minute read
中文简体 中文繁體 日本語 Español
AI Tools

RAGFlow Project Notes: Features and Usage of an Open-Source RAG Engine

A practical overview of infiniflow/ragflow, covering its core positioning, major features, deployment approach, and basic usage flow for enterprise knowledge bases and AI Q&A systems.

2026-04-15
6 minute read
中文简体 中文繁體 日本語 Español
AI Tools

Firecrawl Project Notes: Web Search, Scraping, and Interaction APIs for AI Agents

A concise look at Firecrawl's positioning, core features, use cases, self-hosting options, and licensing boundaries, with a focus on whether it fits as a web data layer for AI agents.

2026-04-15
5 minute read
中文简体 中文繁體 日本語 Español
AI Tools

Playwright CLI Video Recording: Recording, Chapter Markers, Overlays, and Debugging Tradeoffs

Based on the official video-recording reference, this article organizes video capture, chapter markers, Overlay APIs, and the practical differences between video and tracing in Playwright CLI.

2026-04-15
6 minute read
中文简体 中文繁體 日本語 Español
AI Tools

Playwright CLI Session Management: Multiple Browser Sessions, Isolation, Persistence, and Cleanup

Based on the official session-management reference, this article organizes the common ways to use named browser sessions, session isolation, persistent profiles, concurrent usage, and cleanup commands in Playwright CLI.

2026-04-15
6 minute read
中文简体 中文繁體 日本語 Español
Hardware

M.2 Key E, Key B, and Key M Pinout Notes

A concise summary of M.2 pinout documentation, preserving the Pinout Description tables for Key E, Key B, and Key M sockets, with English notes added.

2026-04-15
6 minute read
中文简体 中文繁體 日本語 Español
AI Tools

Playwright CLI storage state: Save Login Sessions, Read Cookies, and Local Storage

Based on the official storage-state reference, this post summarizes the common Playwright CLI commands for storage state, Cookies, localStorage, sessionStorage, and IndexedDB with concise explanations.

2026-04-14
4 minute read
中文简体 中文繁體 日本語 Español
AI Tools

What Is OpenHarness: What This Open Source Agent Harness Can Do

Based on the official HKUDS/OpenHarness repository and README, this article summarizes OpenHarness's positioning, core capabilities, ohmo's personal-assistant features, and the scenarios it fits best.

2026-04-12
6 minute read
中文简体 中文繁體 日本語 Español
1 5 6 7 8 9 10 11 12
© 2022 - 2026 KnightLi Blog
记录并分享
Built with Hugo
Theme Stack designed by Jimmy