#GPU performance optimization
994 related articles
·3 min
Running the 1.56TB Kimi K3 Model on 8GB RAM with Pure C
A developer built a pure C99 inference engine that runs the 1.56TB Kimi K3 model on 8GB RAM using MoE sparsity and NVMe on-demand loading—no GPU, 176KB binary.
Read more →
·3 min
Sorting Algorithm Variants Explained: Semisort, Stable Partition, and K-th Smallest Selection
Deep dive into often-overlooked sorting variants: Semisort, Stable Partition, and K-th smallest selection. Learn how relaxing constraints enables performance breakthroughs.
Read more →
·3 min
MI355X Running Kimi K3 Benchmark: The Logic Behind Outperforming B300 in Performance per Dollar
Deep analysis of AMD MI355X running Kimi K3 with superior cost-efficiency vs NVIDIA B300, and its implications for the AI inference hardware market.
Read more →
·3 min
Persistent State Machines: How INT4 Memory Cells Reshape LLM Attention Mechanisms
Exploring how persistent state machines with INT4-quantized memory cells reshape LLM attention, breaking KV Cache memory bottlenecks for long-context inference on edge devices and high-concurrency scenarios.
Read more →
·4 min
Walsh Multi-Agent Trading System: How Risk Management Veto Power Ensures AI Autonomous Decision-Making Safety
Deep dive into the Walsh multi-agent trading system architecture, exploring how its risk management agent with veto power establishes safety boundaries for AI autonomous decision-making.
Read more →
·3 min
Why Local Agents Crash: A Real-World Report from 4,265 Actual Sessions
A developer spent a month testing 4,265 Claude Code/Codex sessions, revealing why local Agents crash on consumer hardware: tool lists consume 41% of cache, q4_0 quantization traps, and eviction strategy ceilings of only 11.88%.
Read more →
·3 min
Dual RTX 3060 Running DeepSeek V4 Flash: IQ2_M Quantized Inference Benchmarked at 3.5 tok/s
Benchmarking DeepSeek V4 Flash on dual RTX 3060 GPUs with 96GB RAM at IQ2_M quantization achieving 3.5 tokens/sec. Covers hardware choices, 2-bit quantization techniques, and local LLM deployment optimization.
Read more →
·3 min
GPT-5.6 Sol Self-Optimization in Practice: How AI Cuts Its Own Costs and Boosts Its Own Efficiency
GPT-5.6 Sol achieves 20% GPU serving cost reduction and 15%+ token generation efficiency gains through self-optimization. A deep dive into AI recursive efficiency improvement.
Read more →
·3 min
PyTorch vs TensorFlow: How Beginners Should Choose a Deep Learning Framework
Should deep learning beginners choose PyTorch or TensorFlow? This article compares both frameworks on research trends, ecosystem, and deployment, with practical switching advice.
Read more →
·2 min
Running Local LLMs on a 24GB Mac Mini: Model Selection & Speed Optimization Guide
24GB Mac Mini too slow for local LLMs? Learn why 14B models struggle, get 3B-8B model recommendations for Home Assistant, and discover Ollama speed optimization tips.
Read more →
·3 min
LLM Post-Training on an 8GB GPU: A Practical Guide to SFT, DPO, and GRPO
Learn how to complete LLM post-training on a consumer GPU with just 8GB VRAM, covering SFT, DPO, and GRPO methods using LoRA quantization and other techniques.
Read more →
·3 min
Explorative Modeling: How Best-of-K Training Strategies Improve Model Learning Efficiency
Explorative modeling lets models generate K candidate predictions and learn from the best one, introducing exploration into training. This article analyzes Best-of-K training strategy principles, applications, and challenges.
Read more →
·3 min
MiniMax Hailuo H3 Image-to-Video Hands-On: API Experience and Quality Assessment
Hands-on experience with MiniMax Hailuo H3 image-to-video model: API usage, generation quality, community feedback, and comparison with Runway, Pika, and other competitors.
Read more →
·2 min
Terminal Candy: A macOS Terminal Skinning Tool with 84 Color Schemes + Custom Skins
Terminal Candy is a native macOS terminal app with 84 color schemes, CRT retro effects, a visual Skin Builder, and a global hotkey—all for a one-time $10 purchase.
Read more →
·3 min
The Fundamental Conflict Between Backpropagation and Continual Learning: Can Catastrophic Forgetting Ever Be Truly Solved?
Exploring the fundamental conflict between backpropagation and continual learning, analyzing the roots of catastrophic forgetting, limitations of current solutions, and whether local learning or neuromorphic computing can offer true breakthroughs.
Read more →
·6 min
AI Coding Boosts Productivity 10x: Are Programmers Writing Their Own Pink Slips?
A senior developer admits 95% of work is done by Claude Code, with 10x productivity gains. From coding to architecture, AI is eroding programmers' core skill moats. Deep analysis of AI coding's impact on tech employment.
Read more →
·3 min
DeepSeek-V4-Flash Local Deployment Test: $8,000 Hardware Approaches Frontier Model Performance
DeepSeek-V4-Flash-0731 scores 50 on the Intelligence Index, nearly matching the frontier model score of 51 from five months prior. We analyze local deployment, hardware requirements, and implications.
Read more →
·2 min
Opus 5 Generates a Kart Racing Simulator from a Single Prompt: 3D Spatial Understanding Put to the Test
A developer tests Anthropic's Opus 5 model, generating a playable kart racing simulator from a single prompt. Deep analysis of its 3D spatial understanding and industry implications.
Read more →
·3 min
DeepSeek V4 Flash Released: Performance Approaching Claude at Just $0.18 per Million Tokens
DeepSeek V4 Flash launches with benchmark scores approaching Claude Opus 4.8 at just $0.18 per million output tokens. Deep analysis of performance, pricing, and industry impact.
Read more →
·3 min
Ollama + Qwen-Agent: Building a Local Private AI Assistant — From Deployment to Security Best Practices
A complete guide to building a local private AI assistant with Ollama and Qwen-Agent. Covers RAG knowledge integration, voice interaction, and permission isolation for a secure local AI Agent architecture.
Read more →