Tag: architecture
-
视觉语言大模型 VLM 全景：ViT、Projector 桥接层、LLaVA 阶段训练与 DeepSeek-Janus Pro 原理解构
> **核心摘要**：视觉语言大模型 (Vision-Language Models, VLM) 赋予了大语言模型“看懂世界”的能力。VLM 并非从零开始盲目训练，而是巧妙地通过跨模态投影层 (Cross-Modal Projector) 将预训练视觉编码器 (ViT) 抽取的高维图像 Token 映射至 LLM 的文
-
大模型 RAG 与 Agent 生产级系统架构：多租户隔离、流式服务与高可用
> **核心摘要**：将 RAG 知识库与 Agent 应用从 Demo 推向企业生产环境，本质上是分布式系统工程与机器学习工程的交叉问题。本指南自上而下拆解完整技术栈：离线索引流水线（解析 → 分块 → 向量化 → ANN 建索引）、在线服务链路（查询改写 → 混合检索 → 交叉编码重排 → 带引用的流式生成）、Ag
-
AIE Fine-Tuning Guide: Enterprise SFT, LoRA & DPO Alignment
> **Executive Summary**: LLM fine-tuning and alignment empower AI Engineers (AIE) to transform foundation models into domain-specific reasoning engines. In prod
-
MLE Data & Feature Engineering: Quality Pipelines, Categorical Encoding, Imbalance, Selection & Drift Detection
> **Core Executive Summary**: Model performance is decided before training starts — by data quality and feature engineering. This guide covers the full MLE data
-
Agent Design Patterns: ReAct Loop, Reflexion Self-Correction, Plan-and-Execute & Graph Engineering
> **Core Executive Summary**: LLMs are evolving from static question-answering engines into autonomous **AI Agents**. Powered by four core pillars—**Brain (LLM)
-
GPU Hardware Architecture: SM, Tensor Cores, HBM Bandwidth & Roofline Model
> **Core Executive Summary**: AI LLM performance relies directly on underlying GPU hardware physics. Modern GPUs like NVIDIA H100/A100 feature massively paralle
-
Deep Learning Debugging & Competition Engineering Taxonomy: 4-Step Debugging Framework, Single Batch Overfitting, Gradient Check & Grad-CAM Guide
> **Summary**: Debugging deep learning models is notoriously challenging because bad code often runs without crashing while silently degrading performance. This
-
Open & Commercial SOTA LLM Evolution: From BERT/GPT-4 to LLaMA-3, Qwen-3, Gemma-4 & Kimi-K2
> **Core Executive Summary**: Since the Transformer paper, Large Language Models (LLMs) evolved from unidirectional/bidirectional encoders (BERT/GPT-1/2) to lar
-
Unsupervised Clustering & KNN: K-Means++, DBSCAN, GMM-EM & KD-Tree Guide
> **Summary**: Clustering and nearest-neighbor methods form the backbone of pattern recognition and representation analysis. This guide explores coordinate desc
-
Optimization & Matrix Calculus: Lagrange Multipliers, KKT Conditions, SVD & Convergence Geometry
> **Core Executive Summary**: Every machine learning model—from SVM geometric margin maximization to Transformer gradient descent updates—is fundamentally an **