#mixed precision training

140 related articles

Jul 23, 2026·7 min

Context Engineering: A Systematic Approach to Stop AI Agents from 'Talking Nonsense'

Context engineering is the core methodology for building efficient AI Agents, covering query enhancement, RAG retrieval, prompt design, memory management, and tool invocation. Master Write, Select, Compress, and Isolate to solve LLM hallucination at its root.

Jul 23, 2026·4 min

Qwen-Image 3.0 Released: Image Generation Moves Toward Production-Ready Design

Qwen-Image 3.0 supports 4.5K token instructions, 10px text rendering, and 12-language typography for production-ready posters and infographics. Plus: Anthropic settlement, Grok in Excel, Tencent HRAP 1.0.

Jul 23, 2026·4 min

The Rise of Chinese Open-Source AI Models: A Head-On Challenge to Closed-Source Dominance

Chinese open-source models rapidly close the capability gap with top closed-source AI. DeepSeek shocks the industry while Qwen matches global benchmarks.

Jul 22, 2026·3 min

V100 GPU Showdown: 4×16G PCIe vs. 2×32G SXM — Which Gives You More Bang for Your Buck?

Benchmarking 4×V100 16G PCIe vs. 2×V100 32G SXM adapter for local LLM inference. Prefill speed, decode speed, power limits, and bandwidth bottlenecks analyzed.

Jul 22, 2026·3 min

Qwen's Six-Generation Evolution: A Complete Breakdown from Architecture Innovations to the Reasoning Race

From Qwen1 to Qwen3-2507: a complete breakdown of six generations of evolution over two years — GQA, MoE, GRPO, dynamic thinking, and the core shift from architecture to reasoning.

Jul 21, 2026·3 min

Ornith 9B/35B Hands-On: A New Local Deployment Option for Code Agents

Ornith 1.0 by Deep Reinforce reinforces Qwen 3.5 for code agents. We test Ornith 9B & 35B MoE on Chinese writing, logic, and invoice OCR, with full llama.cpp deployment guide.

Jul 20, 2026·3 min

Running a 27B Model on iPhone: How 1-bit Quantization Achieves Extreme Compression

PrismML's Bonsai compresses a 27B model from 54GB to 3.9GB, running at ~11 tokens/sec on iPhone. A deep dive into QAT, knowledge distillation, and speculative decoding.

Jul 20, 2026·7 min

Claude Code Practical Tutorial: A Complete Beginner's Guide to Automating Your Entire Workflow

No coding required! This guide breaks down the complete Claude workflow: custom Projects, batch SEO content, one-sentence tool building with Artifacts, and Claude Code terminal ops—with real traffic-growth cases.

Jul 17, 2026·3 min

Open-Source LLM Surge: K3 and V4 Drop Together as the Marginal Cost of Intelligence Approaches Zero

Kimi K3, DeepSeek V4, Liquid, and Mistral are all dropping at once. MXFP4 quantization and MoE architecture are pushing the marginal cost of intelligence toward zero. Here's what it means.

Bonsai 27B: The First 1-bit LLM That R…

Jul 17, 2026·3 min

Bonsai 27B: The First 1-bit LLM That Runs on Your Phone — A New Milestone for On-Device AI

Bonsai 27B is the first 27B-parameter LLM that runs on smartphones via 1-bit quantization, compressing to 3–4GB. We break down the tech, privacy benefits, and community debate.

Jul 17, 2026·2 min

Running Qwen 122B on 8GB VRAM: A Complete Guide to Quantized Local Deployment

A Bilibili creator ran Qwen 122B with 256K context on just 8GB VRAM + 64GB RAM using llama.cpp. Full breakdown of quantization, deployment params, performance, and cost-effective alternatives.

Jul 17, 2026·3 min

Snowflake ML StandardScaler Error: 'does not index into the dataset' — A Complete Troubleshooting Guide

Fix Snowflake ML StandardScaler's 'does not index into the dataset' error. Learn why Snowflake's identifier case-folding causes column name mismatches and how to resolve them in 3 steps.

Soofi Open-Source Foundation Model Tra…

Jul 16, 2026·2 min

Soofi Open-Source Foundation Model Training Code Deep Dive: The Complete Pipeline from Data to Weights

Soofi is an open-source project providing complete foundation model training code, covering data preprocessing, tokenizer construction, model architecture, and training optimization. A deep dive into its value for the LLM ecosystem.

Jul 15, 2026·2 min

Real-Time Data Augmentation for Single-Class Segmentation Models: Frequency, Combinations, and Boundary Precision Explained

How many augmentations per image is enough? This guide breaks down on-the-fly augmentation strategy for single-class segmentation with 3,000 labeled images, covering controlled mixing, domain matching, and mask boundary precision.

Jul 15, 2026·6 min

The Frontier of AI Interpretability Research: Opening the Neural Network Black Box

An in-depth look at AI interpretability research: from chain of thought and probes to sparse autoencoders, exploring how scientists understand neural network internals and assess AI alignment and safety.

GPT-2 Fine-Tuning Experiment: 88% Func…

Jul 15, 2026·2 min

GPT-2 Fine-Tuning Experiment: 88% Function Calling Success Rate with a 355M Small Model

A developer fine-tuned GPT-2 (355M) on free Kaggle GPUs and achieved 88% function calling success. Here's what this counter-intuitive experiment reveals about small models and LLM agent capabilities.

NVFP4 in Reinforcement Learning Traini…

Jul 14, 2026·2 min

NVFP4 in Reinforcement Learning Training: Stability Challenges and Engineering Practices for 4-Bit Quantization

A deep dive into the stability challenges of NVIDIA NVFP4 (4-bit float) in RL training — covering precision evolution, numerical instability root causes, mixed precision strategies, and dynamic scaling solutions.

JAX Host Offloading: A Practical Guide…

Jul 14, 2026·2 min

JAX Host Offloading: A Practical Guide to Breaking Through LLM Training Memory Bottlenecks

Memory capacity is the core bottleneck in LLM training. This guide explores JAX-based host offloading — covering optimizer state offloading, activation strategies, PCIe bandwidth trade-offs, and how it complements activation recomputation.

Jul 14, 2026·3 min

Krea 2 Style Prompts in Practice: A Complete Breakdown of 17 Artistic Styles

A deep dive into 17 style prompts for Krea 2, covering Rembrandt lighting, Mucha Art Nouveau, hyperrealistic anime, and more. Learn content-style decoupling for precise AI image generation.

Jul 13, 2026·2 min

Distributed AI Systems: A Practical Engineering Guide to Training, Inference, and Production Deployment

A deep dive into distributed AI systems engineering: data/model/tensor parallelism for training, KV cache, quantization, elastic scaling for inference, and cloud deployment with Kubernetes, Ray, and DeepSpeed.