332 related articles
NVIDIA GQE Deep Dive: How GPU Query En…
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.

Why memory bandwidth (GB/s), not VRAM size, determines local LLM inference speed. Includes tokens/sec formula, GPU bandwidth comparison, and a practical card selection framework.

Learn why memory bandwidth (GB/s)—not VRAM size—determines local LLM inference speed. Get the tokens/sec formula, GPU bandwidth comparisons, and a practical card selection hierarchy.

Deep analysis of the SDL_GPU single-header 2D graphics library covering its design philosophy, GPU acceleration principles, use cases, and technical trade-offs.

Speech To Markdown is a free macOS/iOS app that converts voice to structured Markdown notes using local LLMs. Fully offline, no API keys needed, with global hotkey dictation.

Analyzing real LLM inference costs: from B200 GPU compute gains, vLLM framework optimization to MTP multi-token prediction, explaining why serving costs are widely overestimated.

OpenAI's internal model GPT-5.6 reportedly autonomously rewrites production kernels, achieving ~20% service cost reduction. Deep analysis of this AI recursive self-optimization event's technical plausibility and industry impact.

OpenAI's internal model GPT-5.6 reportedly autonomously rewrote production compute kernels, achieving ~20% cost reduction. Deep analysis of this AI recursive self-optimization event's technical plausibility, industry impact, and key questions.

Local LLM crashing in Agent frameworks? The issue may be num_gpu set too high. Learn what num_gpu really controls (GPU layer offloading, not GPU count) and how to tune it for stable Agent performance.

Complete guide to deploying production-grade LLM inference on Kubernetes, covering GPU scheduling, vLLM engine selection, autoscaling, observability, and cost optimization.

A deep dive into LLM inference cost structure and profitability models—from GPU throughput, MoE architecture, and KV Cache to scale effects—revealing the business logic behind API price wars.

Moonshot AI open-sources FlashKDA, providing high-performance CUDA kernels for Kimi Delta Attention. Learn about its technical principles, performance gains, and value for long-context training and inference acceleration.

Moonshot AI open-sources FlashKDA, providing high-performance CUDA kernels for Kimi Delta Attention. Explore its technical principles, performance gains, and value for long-context training and inference.

Deep dive into the maderix/ANE GitHub project that reverse engineers Apple's private APIs to enable neural network training on the Apple Neural Engine, exploring its technical approach, efficiency gains, compliance risks, and implications for on-device AI.

Chip stocks fall simultaneously across U.S. and Asian markets as AI bubble fears intensify. Analysis of the drivers, sustainability of AI capex, and the balance between short-term volatility and long-term trends.

Chip stocks decline simultaneously across US and Asian markets as AI bubble fears intensify. Analysis of the logic behind the selloff, sustainability questions around AI capex, and the relationship between short-term volatility and long-term trends.

A deep dive into Kimi Delta Attention (KDA): tracing the evolution from quadratic Softmax attention through linear attention, Delta rules, and gated decay mechanisms, with insights on associative memory and hardware optimization.

Deep dive into Kimi Delta Attention (KDA): from standard Softmax attention's quadratic bottleneck through linear attention, Delta Rule, and gated decay mechanisms — the complete evolution explained.

Facing GPU fragmentation on edge devices, the PostSlate team used ncnn's Vulkan backend for cross-platform ML inference, achieving 10× speedup on RTX 4070 with half the model size and zero runtime installation.

Moonshot AI launches Kimi K3 with 2.8 trillion parameters and 1M token context. Google delays Gemini 3.5 Pro, AI coding tools upgrade collectively as competition shifts to coding and Agent capabilities.