Insights and hands-on guides on frontend, backend, databases, IT infrastructure, and AI solutions.
Running an LLM on CPU Only - Real Numbers from an Old Xeon with 256GB RAM
Our Servers Catch Burglars Every Day - TREEWALL Field Test Report
NVMe Storage Benchmark: Optane to HDD - 20 Devices Compared with fio
Local AI Video Generation with ComfyUI + Wan 2.2 - An RTX PRO 6000 96GB Build Log
Structuring Unstructured Documents with an LLM - Measured Accuracy on a 19-Item Menu
Zero API cost, unrestricted commercial use. A local video generation pipeline built with Wan 2.2, LTX 2.3, and MOVA — from model selection and storage design to one-line API automation.
NVIDIA driver 590→595 upgrade benchmarks on RTX PRO 6000 Blackwell — SGLang inference speed, CUDA compute, P-State changes, and operational warnings.
At $450, the RTX 5060 Ti delivers 35% of the RTX PRO 6000's performance. Combined, they boost throughput by 70% for just 9% additional cost.
The RTX 5060 Ti runs 8B models at 76 tok/s and handles 30 concurrent users with zero errors. Here is the complete benchmark at $450.
Qwen3-14B-AWQ scored 3.86 overall across 60 questions on two GPUs — first place among 6 models. Here are its strengths and critical weaknesses.
Running 7 tenants on one GPU with 5 LoRA adapters, we executed 15 isolation tests to verify zero cross-tenant data leakage.
vLLM looks faster at median latency. But at P95, SGLang wins by 6.5x. With 3x throughput and zero errors at 200 users, we explain why P95 matters more than median for production LLM serving.
Comparing 6 local LLMs across e-commerce, legal, and business automation scenarios — revealing dangerous hallucination patterns in legal AI.
Comparing 6 local LLMs on Korean fluency — honorifics, business tone, language contamination (Chinese/English mixing), and natural expression across 10 practical questions.
Guarding the Front Door of Your Network - TREEWALL, an AI Security Gateway
Build a CCTV Recording Server Without an NVR - RTSP + ffmpeg + systemd, 180-Day Retention
Our MoE Model Started Spewing Garbage - What Auditing All 18,432 Expert Weights Revealed
What We Learned Building and Auditing 990 AI-Generated English Learning Scenes
BGE-M3 vs mE5-Large - Comparing Korean RAG Search Quality Head to Head
