Tag: #optimization

한국어English日本語中文

← All posts

• Optimizing Long-Context Inference with Hybrid SWA — What Xiaomi's MiMo v2.5 Actually Does

  Hybrid SWA interleaves sliding-window attention with full attention across layers to cut both KV-cache memory and compute for long-context inference — now a mainstream design. Grounded in Xiaomi's published MiMo v2.5 inf

  2026-07-11 · 7 min read #ai#llm#inference#attention#optimization

• The State of LLM Quantization — From GPTQ and AWQ to FP8, MXFP4, and KV-Cache Quantization

  Quantization represents a model's numbers in fewer bits to cut memory and cost. Why quality survives fewer bits (outliers and scaling), how GPTQ and AWQ differ in approach, llama.cpp GGUF k-quants, QLoRA's NF4, the 2026

  2026-07-08 · 7 min read #ai#llm#quantization#inference#optimization

• The 3D Pipeline — Real-Time Games vs. Offline Film

  This guide surveys the entire 3D asset pipeline from modeling to rendering. It organizes how the real-time rendering of game engines differs from the offline render farms of film, optimization concepts like LOD, poly bud

  2026-06-27 · 17 min read #3d-pipeline#real-time#offline-rendering#game-engine#gltf

• Making Inference Fast — Quantization, Sparsity, and Dataflow from a Hardware Lens

  We break down the cost structure of inference through the memory-wall lens, then connect quantization (INT8/FP8/FP4), structured sparsity (2:4), dataflow architectures, operator fusion, batching and KV caching into one p

  2026-06-16 · 18 min read #inference#quantization#sparsity#dataflow#gpu

• Game Development Complete Guide 2025: Unity vs Unreal vs Godot, ECS, Multiplayer, Optimization

  Everything about game development! Unity DOTS/ECS, Unreal Engine 5 (Lumen/Nanite), Godot 4, game loops, physics engines, multiplayer (Netcode/Mirror), performance optimization (draw calls/batching), mobile vs console vs

  2026-04-15 · 12 min read #game-development#unity#unreal-engine#godot#ecs

• Compiler & Interpreter Design Complete Guide 2025: Lexer, Parser, AST, Code Generation

  Everything about compiler/interpreter design! Lexer (tokenization), Parser (syntax analysis/recursive descent/Pratt), AST (abstract syntax tree), semantic analysis (type checking), IR (intermediate representation), code

  2026-04-14 · 31 min read #compiler#interpreter#lexer#parser#ast

• Backend Performance Engineering Complete Guide 2025: Profiling, Load Testing, Bottleneck Analysis, Optimization

  Everything about backend performance! Profiling (CPU/Memory/I-O), load testing (k6/Artillery/Locust), bottleneck analysis (DB/Network/CPU/Memory), N+1 resolution, connection pool tuning, caching strategies (Redis/CDN/App

  2026-04-14 · 21 min read #backend-performance#profiling#load-testing#optimization#k6

• Advanced Prompt Engineering Complete Guide 2025: CoT, ToT, Self-Consistency, Meta-Prompting

  Advanced Prompt Engineering! Chain-of-Thought(CoT), Tree-of-Thought(ToT), Self-Consistency, ReAct, Meta-prompting, Structured Output(JSON Mode), System Prompt design, Few-shot optimization, Prompt Chaining, Evaluation(au

  2026-04-14 · 21 min read #prompt-engineering#chain-of-thought#tree-of-thought#few-shot#system-prompt

• FinOps & Cloud Cost Optimization Complete Guide 2025: AWS/GCP/Azure Cost Reduction Strategies

  Everything about FinOps! Cloud cost visibility (Cost Explorer/Billing), optimization strategies (Reserved/Spot/Savings Plans), resource right-sizing, auto-scaling, storage tiering, K8s costs (Kubecost), AI/ML cost manage

  2026-04-13 · 23 min read #finops#cloud-cost#optimization#aws#gcp

• Complete Guide to LLM Fine-tuning with Unsloth 2025: QLoRA, 4-bit Quantization, 2x Faster Training

  Everything about LLM fine-tuning with Unsloth! QLoRA/LoRA theory, 4-bit quantization (bitsandbytes), Unsloth 2x speed secret, Llama 3/Mistral/Qwen fine-tuning, data preparation, training config, VRAM optimization, GGUF/G

  2026-03-25 · 17 min read #unsloth#llm#fine-tuning#qlora#lora

• Engineering Math Series 24: Numerical Methods, Optimization, Graphs, Probability and Statistics Roadmap

  Wraps up the first cycle of the engineering math series and organizes why numerical methods, optimization, graphs, and probability and statistics matter, plus the recommended study order.

  2026-03-19 · 4 min read #engineering-math#numerical-methods#optimization#probability#statistics

• AI Model Serving and Inference Optimization Complete Guide: vLLM, TensorRT, Triton, Ollama

  The complete guide to efficiently serving AI models in production. Master vLLM, TensorRT, NVIDIA Triton Inference Server, Ollama, quantization (INT8/INT4), batch processing, and latency optimization with real-world examp

  2026-03-17 · 19 min read #mlops#model-serving#vllm#tensorrt#triton

• Mathematical Optimization for Machine Learning: From Adam to Convex Optimization and ZeRO

  A comprehensive guide to ML training optimization covering SGD, Adam, AdamW, Lion optimizer, cosine annealing scheduling, Focal Loss, InfoNCE, and ZeRO optimizer.

  2026-03-17 · 12 min read #optimization#adamw#learning-rate-scheduling#loss-functions#convex-optimization

• Deep Learning Debugging Complete Guide: From Diagnosing Training Failures to Performance Optimization

  A complete guide to systematically diagnosing and resolving deep learning training failures. Covers Loss NaN, vanishing/exploding gradients, overfitting, slow convergence, and out-of-memory errors with real-world code ex

  2026-03-17 · 19 min read #deep-learning#debugging#pytorch#training#optimization

• Deep Learning Training Methods Complete Guide: From Optimization to Distributed Training

  A comprehensive guide covering all techniques for effectively training deep learning models. Learn gradient descent, optimizers, learning rate scheduling, regularization, batch normalization, transfer learning, fine-tuni

  2026-03-17 · 28 min read #deep-learning#training#optimization#regularization#distributed-training

• LLM Inference Optimization Complete Guide: KV Cache, Speculative Decoding, Continuous Batching

  A complete guide to pushing LLM inference to its limits. Covers KV Cache, Speculative Decoding, Continuous Batching, PagedAttention, FlashInfer, multi-GPU inference, and DeepSeek MLA in depth.

  2026-03-17 · 25 min read #llm#inference#optimization#kv-cache#speculative-decoding

• LLM Quantization Comparison Guide — GPTQ, AWQ, GGUF, bitsandbytes Practical Application

  A comparative guide to LLM quantization techniques including GPTQ, AWQ, GGUF, and bitsandbytes with practical application tips.

  2026-03-09 · 24 min read #llm#quantization#gptq#awq#gguf

• Math + LaTeX/KaTeX Complete Guide for Reading AI/ML Papers

  A comprehensive summary of essential math concepts (linear algebra, calculus, probability/statistics, optimization) and LaTeX/KaTeX formula syntax for reading AI/ML papers with practical examples, symbol cheat sheets, an

  2026-03-08 · 20 min read #ai-papers#math#latex#katex#linear-algebra

• N+1 Problem Deep Dive — The Silent Performance Killer in ORMs

  What the N+1 problem is, why it is dangerous, how to find it, and how to fix it. A complete guide with practical code covering solutions across all ORMs including Django, SQLAlchemy, JPA/Hibernate, Prisma, and ActiveReco

  2026-03-02 · 10 min read #database#n-plus-1#orm#django#sqlalchemy

• Accelerating LLM Inference 2-3x with Speculative Decoding: From Theory to Production

  A deep dive into the mathematical foundations of Speculative Decoding, the Draft-Verify pipeline, acceptance probability analysis, practical implementation in vLLM/TensorRT-LLM, and Apple's Mirror Speculative Decoding.

  2026-03-02 · 8 min read #llm#speculative-decoding#inference#optimization#vllm