Tag: #llm

한국어English日本語中文

← All posts

• 2025 Open Source AI Models Showdown: DeepSeek R1 vs Llama 4 vs Qwen 3 vs Mistral

  DeepSeek R1 (671B/37B), Llama 4 Scout/Maverick, Qwen 3 (235B MoE), Mistral 8x22B — complete comparison of the 2025 open-source AI model leaders with benchmarks, licenses, deployment guides, and cost analysis.

  2026-03-22 · 20 min read #open-source#ai#llm#deepseek#llama

• Toss Bank ML Engineer (MLOps) Complete Guide: From MLFlow to LLM Platform — Tech Stack Deep Dive

  Complete analysis of Toss Bank ML Platform Team MLOps Engineer JD. Deep dive into MLFlow, Airflow, JupyterHub, Kubeflow, Triton Inference Server, ScyllaDB Feature Store, and LLM platform — with 30 interview questions and

  2026-03-21 · 38 min read #mlops#ml-platform#tossbank#kubernetes#mlflow

• 2025 AI Research Trends: Top HuggingFace Papers and 10 Defining Research Directions

  A developer-focused review of HuggingFace trending papers and the 10 defining AI research trends of 2025. DeepSeek-R1 pure RL reasoning, Nemotron-Cascade 30B/3B MoE, GRPO, PagedAttention, million-token context limitation

  2026-03-21 · 15 min read #ai-research#papers#huggingface#reasoning#moe

• AI Supercomputer at Home: Study LLMs on NVIDIA DGX Spark and Create Content with ComfyUI

  Run 200B-parameter LLMs locally on NVIDIA DGX Spark ($3,999) and generate FLUX/SDXL images with ComfyUI. Complete guide with specs, benchmarks, setup instructions, and cost analysis — the era of personal AI supercomputer

  2026-03-21 · 37 min read #nvidia#dgx-spark#comfyui#local-ai#llm

• [Architecture] Complete Guide to LiteLLM: Unified Serving of 100+ LLMs

  A comprehensive guide on integrating 100+ LLMs through a single API with LiteLLM, covering Proxy server setup, cost tracking, rate limiting, load balancing, and production deployment.

  2026-03-20 · 15 min read #architecture#litellm#llm#ai-gateway#mlops

• RAG vs Fine-tuning vs Prompt Engineering: The Complete Decision Framework

  A practical comparison of RAG, fine-tuning, and prompt engineering from a production engineering perspective, with a concrete decision framework, real cost calculations, and honest gotchas from building these systems in

  2026-03-18 · 7 min read #rag#fine-tuning#prompt-engineering#llm#ai-development

• Tool Calling in Practice: How AI Interacts with the World and Common Pitfalls

  Tool calling is what transforms an LLM from a text transformer into an agent that can actually do things. Full implementation of OpenAI function calling and Claude tool use, parallel execution patterns, and the five mist

  2026-03-18 · 9 min read #tool-calling#function-calling#ai-agent#llm#ai-development

• LLM Agent Design Patterns: From ReAct to Multi-Agent Orchestration

  ReAct, Chain of Thought, Plan-and-Execute, Reflection, Tree of Thoughts — a practical breakdown of which LLM agent design pattern to use and when, from an engineer who has built them in production.

  2026-03-18 · 9 min read #ai-agent#react#llm#design-patterns#ai-development

• Prompt Engineering 2025: Getting Maximum Performance from Modern LLMs

  Even the best model gives poor results with a poor prompt. Six prompt engineering techniques proven in production, with working code for GPT-4o, Claude, and open-source models.

  2026-03-18 · 7 min read #prompt-engineering#llm#ai-development#gpt-4o#claude

• LLM Hallucination: Why AI Makes Things Up and 5 Strategies to Prevent It

  A technical deep-dive into why LLMs hallucinate, covering all four hallucination types and five practical prevention strategies including RAG, self-critique pipelines, Chain of Verification, and temperature tuning — all

  2026-03-18 · 9 min read #hallucination#llm#ai-reliability#ai-development#rag

• 1 Million Token Context Windows: Is RAG Becoming Obsolete?

  With Gemini 1.5 Pro's 1M token context and Claude's 200K, many developers ask: why bother with RAG? We compare real costs, latency, and quality to give you an honest answer.

  2026-03-18 · 6 min read #context-window#rag#llm#long-context#ai-development

• Fine-tuning in Practice: Building Your Own Model with LoRA and QLoRA

  You don't need 7 H100s. With LoRA and QLoRA, you can fine-tune a 70B model on a single consumer GPU. A practical end-to-end guide with working code.

  2026-03-18 · 7 min read #fine-tuning#lora#qlora#llm#ai-development

• Complete Guide to Open Source LLMs: Llama 3, Mistral, DeepSeek, Qwen, and Gemma

  A comprehensive overview of the open source LLM landscape covering Llama 3, Mistral, DeepSeek, Qwen, and Gemma.

  2026-03-17 · 14 min read #llm#llama#mistral#deepseek#qwen

• Complete Guide to LLM Evaluation and Benchmarking: MMLU, MT-Bench, RAGAS, LM-Eval

  A complete guide to evaluating LLMs correctly. Covers standard benchmarks such as MMLU, MT-Bench, and HumanEval, evaluating RAG systems with RAGAS, practical use of LM-Evaluation-Harness, and building production LLM eval

  2026-03-17 · 17 min read #llm#evaluation#benchmark#ragas#lm-eval

• Building LLM from Scratch: Complete Guide to Understanding GPT through Code

  A complete guide to building and understanding Large Language Models from scratch. Implement a full GPT architecture in PyTorch — from tokenizer to Transformer, pretraining, and fine-tuning.

  2026-03-17 · 21 min read #llm#gpt#transformer#from-scratch#deep-learning

• LLM Fine-tuning Complete Guide: Master LoRA, QLoRA, RLHF, and DPO

  A complete guide covering every LLM fine-tuning technique. From Full Fine-tuning to LoRA, QLoRA, RLHF, DPO, and Instruction Tuning — master them all with HuggingFace PEFT and hands-on examples.

  2026-03-17 · 21 min read #llm#fine-tuning#lora#qlora#rlhf

• Complete Guide to Korean NLP and LLM: Mastering KoBERT, KLUE, HyperCLOVA, and EXAONE

  A comprehensive guide to Korean NLP and LLM covering KoBERT, KLUE, HyperCLOVA, and EXAONE.

  2026-03-17 · 27 min read #korean-nlp#kobert#klue#hyperclova#exaone

• Torch-Titan Complete Guide: Everything About Large-Scale Distributed Training with PyTorch

  A complete guide to mastering large-scale LLM distributed training with PyTorch Titan (torchtitan). Covers FSDP2, pipeline parallelism, tensor parallelism, 4D parallelism, Flash Attention, and mixed precision with hands-

  2026-03-17 · 19 min read #torch-titan#distributed-training#pytorch#fsdp#deep-learning

• Deep Learning Recommendation Systems Complete Guide: From Collaborative Filtering to LLM-based RecSys

  A complete guide to recommendation systems from foundations to the latest deep learning techniques. Master collaborative filtering, Matrix Factorization, NCF, Two-Tower models, sequential recommendation, GNN-based approa

  2026-03-17 · 18 min read #recommendation-system#collaborative-filtering#deep-learning#two-tower#llm

• RAG Systems Complete Guide: Everything About Retrieval-Augmented Generation

  A complete guide to mastering RAG (Retrieval-Augmented Generation) systems. From basic RAG to advanced Self-RAG, Corrective-RAG, and HyDE — covering vector databases, embedding models, chunking strategies, and reranking

  2026-03-17 · 23 min read #rag#llm#vector-database#langchain#embedding