Blog

#2026-03 765#english 592#culture 264#deep-dive 254#kubernetes 249#career 229#ai 219#llm 209#devops 196#2026-04 146#security 143#database 114#observability 113#communication 109#history 107#architecture 100#productivity 96#finance 88#economy 84#mindset 81#psychology 80#ai-papers 79#food 78#it 78#travel 78#deep-learning 77#japanese 77#networking 77#performance 72#business-travel 70#linux 70#gpu 69#ai-agent 66#cs-fundamentals 63#postgresql 61#rag 58#self-improvement 55#learning 53#mlops 53#python 52

• Choosing Speech Models: Practical Criteria for STT and TTS

  Unlike text models, speech models are chosen after the language coverage, audio length constraints, real-time requirement, and diarization need are already fixed. This post lays out the parameters, licenses, language cov

  2026-08-12 · 7 min read #ai#huggingface#open-source-llm#speech-to-text#text-to-speech

• Choosing Open Text Generation Models by Size Class

  When picking an open text generation model, size is not a quality tier — it is a deployment constraint. This post splits the field into on-device small, single-GPU mid, and server-class large, listing the parameters, con

  2026-08-12 · 7 min read #ai#llm#huggingface#open-source-llm#text-generation

• Open Models That Support Korean, and the Cost of Tokenization

  A line saying a model supports Korean means it processes the language, not that it is good at it. This post lays out the card values read on 2026-08-12 for Korean-focused, bilingual, and multilingual open models, explain

  2026-08-12 · 6 min read #ai#llm#huggingface#open-source-llm#korean-nlp

• Licenses and Deployment: Reading the Types and Verifying Quantized Builds

  The short identifier in an open model license field is a table of contents; the actual terms live in the full text. This post organizes the license types actually encountered on 2026-08-12, what community licenses and no

  2026-08-12 · 7 min read #ai#llm#huggingface#open-source-llm#license

• Choosing Code Models: Completion vs Chat, FIM, and Licenses

  Code models come in two different products: the completion model that fills the cursor position inside an editor, and the conversational model that answers questions. This post organizes the parameters, context, fill-in-

  2026-08-12 · 7 min read #ai#llm#huggingface#open-source-llm#code-llm

• Vision and Multimodal: Image Understanding, OCR, and VLMs

  Vision models are not one category. Conversational VLMs, dedicated OCR, document structuring, and image retrieval embeddings are different objects and do not substitute for one another. This post organizes the card value

  2026-08-12 · 7 min read #ai#huggingface#open-source-llm#vision-language-model#ocr

• How to Read a Hugging Face Model Card: What to Trust and What to Doubt

  Six fields on a Hugging Face model card actually carry decision weight: license, parameter count, context length, intended use, limitations, and training data. This post explains what each field means and what it hides,

  2026-08-12 · 7 min read #ai#llm#huggingface#open-source-llm#model-card

• Embeddings and Rerankers: What Actually Matters in RAG

  What decides your embedding model in a RAG build is not a leaderboard rank but dimensionality, maximum input length, prefix conventions, multilingual coverage, and the division of labor with a reranker. This post lays ou

  2026-08-12 · 7 min read #ai#llm#huggingface#open-source-llm#embedding

• FDE Interview Prep — Diagnosis Scenarios, Customer Simulations, Case Studies

  A Forward Deployed Engineer (FDE) interview often replaces algorithm puzzles with incident-diagnosis scenarios on an unfamiliar system, and culture-fit questions with an angry-customer role play — because what it measure

  2026-08-12 · 5 min read #career#fde#forward-deployed-engineer#interview#job-search

• Inside vLLM (5) — Prefix Caching, and Why System Prompt Design Is Performance

  A rundown of when vLLM prefix caching hits and when it misses, based on the official design document. Covers how block hashes chain to the block before them, why only full blocks get cached, how a single timestamp placed

  2026-08-12 · 7 min read #vllm#prefix-caching#kv-cache#prompt-engineering#llm

• Inside vLLM (3) — How Continuous Batching Keeps the GPU Busy

  Explains why static batching leaves the GPU idle, and how vLLM iteration-level scheduling removes that idle time. Covers the difference in character between prefill and decode, V1 unified scheduler and its token budget,

  2026-08-12 · 7 min read #vllm#continuous-batching#chunked-prefill#llm#inference

• Inside vLLM (7) — Deployment Tuning, Common Pitfalls, and OOM Triage

  A practical order for tuning a vLLM deployment. Covers what gpumemoryutilization actually sets, when to use tensor parallelism versus pipeline parallelism, how to choose quantization and a KV cache data type, and a diagn

  2026-08-12 · 10 min read #vllm#gpu#quantization#tensor-parallel#llm

• Inside vLLM (2) — Why PagedAttention Splits the KV Cache Into Pages

  Explains why PagedAttention splits the KV cache into fixed-size blocks, verified against the original paper (arXiv:2309.06180) and the official vLLM design documentation. Covers the internal and external fragmentation th

  2026-08-12 · 7 min read #vllm#paged-attention#kv-cache#llm#gpu

• Inside vLLM (6) — Context Window vs max_model_len vs max_tokens, Fully Explained

  If the difference between context window and maxtokens has been confusing, this single post sorts it out. Covers what each of the following actually limits, with a comparison table and real error messages: the context wi

  2026-08-12 · 12 min read #vllm#context-window#max-model-len#max-tokens#llm

• Inside vLLM (4) — The Scheduler and Preemption, Where Throughput Collapses ♪ Listenable

  Explains what the vLLM scheduler decides on every step, how the waiting queue and running list move, and how preemption, triggered when the KV cache runs short, wrecks latency and throughput, verified against the officia

  2026-08-12 · 7 min read #vllm#scheduler#preemption#kv-cache#llm

• Inside vLLM (1) — The Full Path From One Request to One Token

  Follows the full path a single request takes through vLLM, from arrival to the first token out. Covers what the API server, scheduler, KV cache manager, worker, and sampler each do, and how the process layout splits afte

  2026-08-12 · 6 min read #vllm#llm#inference#gpu#ai-platform

• Video Generation and Understanding Technical Reports: What to Read, and Why Constraints Beat Demos

  Ten video generation and understanding technical reports, each verified by opening the arXiv abstract page directly. CogVideoX, Movie Gen, HunyuanVideo, LTX-Video, Wan, Seedance 1.0 and 2.0, plus Qwen2.5-VL, VideoLLaMA 3

  2026-08-12 · 7 min read #ai-papers#paper-review#technical-report#video-generation#diffusion-transformer

• Text LLM Technical Reports: What to Read, and How to Read Design Decisions Instead of Rankings

  Nine text-LLM technical reports, each verified by opening the arXiv abstract page directly. What DeepSeek-V3, DeepSeek-R1, Qwen3, Gemma 3, Olmo 3, Kimi K2, MiniMax-01, Mellum2 and s1 each did that was new, and which limi

  2026-08-12 · 7 min read #ai-papers#paper-review#technical-report#llm#moe

• The Training Recipe — From Pre-training to Post-training, and What Reports Write Down

  Comparing, exactly as written in the reports, the three stages and six context extensions of Llama 3, the three-stage pre-training of Qwen3, the learning-rate schedule and two-phase YaRN extension of DeepSeek-V3, and the

  2026-08-12 · 6 min read #ai-papers#model-internals#pretraining#training-recipe#data-mixture

• Positional Encoding — RoPE and the Price of Context Extension

  Showing through wavelength arithmetic how a single ropetheta value acts on context length, then comparing the 500000 of Llama 3, the ABF step in Qwen3, the YaRN settings of DeepSeek-V3 and Kimi K2, and the partial rotati

  2026-08-12 · 6 min read #ai-papers#model-internals#rope#positional-encoding#long-context