#arithmetic intensity
14 related articles
·6 min
AI Application Engineer Interview Guide: Core Topics in Model Quantization and Inference Deployment
A systematic review of must-know topics for AI Application Engineer interviews: PTQ/QAT quantization, operator fusion, inference pipelines, latency/throughput analysis, and edge deployment of detection/segmentation/BEV models.
Read more →
·6 min
AI Application Engineer Interview Guide: Core Topics on Model Quantization and Inference Deployment
A systematic guide to must-know AI application engineer interview topics: PTQ/QAT quantization, operator fusion, inference pipelines, latency/throughput analysis, and edge deployment of detection/segmentation/BEV models.
Read more →
·4 min
DeepSeek Open-Sources DeepSpec: A Full-Stack Breakdown of Speculative Decoding
DeepSeek open-sources DeepSpec, a full speculative decoding training and evaluation toolkit featuring three draft model algorithms (Ego3, DeepFlash, DeepSpark), 12 checkpoints, MIT license, and 60–85% real-world speedup.
Read more →
CUDA Kernel Fusion: A Practical Guide …
·2 min
CUDA Kernel Fusion: A Practical Guide to Reducing Memory Bandwidth and Launch Overhead
Learn how CUDA Kernel Fusion merges multiple GPU kernels to reduce global memory traffic and launch overhead, with real-world examples from AI inference and deep learning.
Read more →
Voice-Driven Geometric Interaction: LL…
·2 min
Voice-Driven Geometric Interaction: LLM Semantic Parsing and Function Calling Architecture in Practice
How can LLMs translate natural language into geometric operations? This article breaks down a voice-driven geometry system: LLM for semantic parsing, Function Calling to bridge the geometry SDK.
Read more →
·6 min
GPT-5.6 vs Grok 4.5 on the Same Day: A Packed Week of Flagship AI Model Launches
OpenAI's GPT-5.6 launches with Sawa, Terra, and Luna sub-models the same day as Musk's Grok 4.5, while Anthropic, Meta, and NVIDIA make their moves. A packed week of flagship AI launches.
Read more →
·5 min
TensorRT Multi-Device Inference: Engineering Practices for Breaking Through Single-GPU Memory Bottlenecks
NVIDIA TensorRT now supports multi-device inference via pipeline and tensor parallelism, distributing large models across multiple GPUs to break through single-card memory limits.
Read more →
·6 min
AMD MI355X Running GLM5.2: Inference Costs at Half of NVIDIA Blackwell
AMD MI355X achieves 2,626 tokens/sec throughput running GLM5.2 at half the TCO of NVIDIA Blackwell. Deep analysis of the technical logic, ROCm ecosystem progress, and market implications.
Read more →
·4 min
NVFP4 Quantization in Practice: A Guide to Compressing Large Models with NVIDIA Model Optimizer
Deep dive into NVFP4 quantization: using NVIDIA Model Optimizer to compress Nemotron 3 Ultra to FP4 checkpoints, reducing memory by 75% and boosting inference throughput on Blackwell GPUs.
Read more →
·3 min
DeepSeek Open-Sources DiSpark: Up to 85% Faster AI Inference Without Changing Hardware
DeepSeek and Peking University release DiSpark, an open-source framework that speeds up LLM inference by 60–85% using speculative decoding and hierarchical verification — no hardware changes or retraining required.
Read more →
NVIDIA Nsight Tools in Practice: A Per…
·3 min
NVIDIA Nsight Tools in Practice: A Performance Optimization Guide for Neural Reconstruction Pipelines
Learn how to optimize neural reconstruction pipelines using NVIDIA Nsight Systems and Nsight Compute — from CPU-GPU sync blocking to kernel-level profiling for autonomous driving simulation.
Read more →
NVIDIA GQE Deep Dive: How GPU Query En…
·2 min
NVIDIA GQE Deep Dive: How GPU Query Engines Break Through Memory Bandwidth Bottlenecks
A deep dive into NVIDIA GQE's architecture: how HBM, NVLink, and memory-hierarchy-aware execution models help GPU query engines overcome I/O and bandwidth bottlenecks.
Read more →
·3 min
GLM-4 Open Source Strikes Back: The AI War Expands to Memory and Space Computing
Zhipu AI's GLM open-source model approaches top closed-source models at 15% of GPT-5.5's cost. HBM shortages fuel AI inflation, and space data centers emerge as a serious compute play.
Read more →
Industry Insights·2 min
Why Musk Abandoned Ground-Based Solar: The Truth Behind xAI's Shift to Natural Gas
Musk's xAI embraces natural gas for data centers while SpaceX bets on space solar. Why did this former solar advocate pivot? A deep dive into AI-era energy challenges.
Read more →