Три фикса, четыре ошибки, один файл
# Как мы четыре раза неправильно диагностировали зависание на джобе 281 339 Несколько месяцев назад я писал, [как мы четыре раза неправильно чинили ме…
Latest Web news from Tech News
All topics
AI
agents
ai
api
architecture
automation
aws
beginners
career
claude
database
devchallenge
devops
javascript
learning
linux
llm
machinelearning
mcp
opensource
performance
productivity
programming
python
react
security
showdev
tutorial
typescript
webdev
Why You Need to Become a Neuro-Punk Right Now
A short essay on why the developer community should invest as much effort as possible into LLMs that are free from corporations and states. ML researc…
nvidia-smi Reports 97% Utilization While the GPU Sits Idle
TL;DR A GPU shows 97% utilization in nvidia-smi , but training throughput is a fraction of what benchmarks promise. The GPU is not computing; it is wa…
Cколько железа нужно ИИ-агенту? Как мы считали ресурсы для on-premise LLM и почему калькуляторы ошиблись в 5 раз
На связи Сергей Смирнов, AI-инженер и основатель LLMStart.ru. Один из самых частых вопросов от бизнеса: «Сколько и какого железа нужно, чтобы разверну…
CUDA for AMD Lemonade, Intel Arc Pro Linux Gains, XPU Manager 2.0
CUDA for AMD Lemonade, Intel Arc Pro Linux Gains, XPU Manager 2.0 Today's Highlights Today's top GPU news highlights include AMD's Lemonade SDK gainin…
G4 Fractional VMs are now available on Google Cloud!
In 2025 Google Cloud added G4 , powered by NVIDIA's RTX PRO 6000 Blackwell Server Edition GPUs to their offering, allowing them to offer hardware not …
Flash Attention: what it does and why it matters
Flash Attention: what it does and why it matters Your training job is paying for an A100 at $3/hour. The loss is going down, gradients are flowing, an…
Vortex 3.0 RISC-V GPGPU, Pragtical SDL GPU Backend, NVIDIA RTX Spark Launch
Vortex 3.0 RISC-V GPGPU, Pragtical SDL GPU Backend, NVIDIA RTX Spark Launch Today's Highlights Today's top stories highlight significant advancements …
How to Tune llama.cpp --n-gpu-layers: A Practical VRAM Guide (2026)
You already know what --n-gpu-layers does. It moves transformer layers onto your GPU. This post is the next step: how to actually pick the number. If …
GPU_WORKLOAD_MISMATCH: A Novel Security Finding Category for AI Container Workloads
Defensive Publication: GPU_WORKLOAD_MISMATCH A Novel Security Finding Category for AI Container Workloads Author: Carnell Smith, Champtron Systems LLC…
Linux 7.1 Boosts Intel Arc, Flatpak Integrates ROCm, Vintage AMD Driver Refined
Linux 7.1 Boosts Intel Arc, Flatpak Integrates ROCm, Vintage AMD Driver Refined Today's Highlights Recent developments enhance GPU performance and acc…
I Tested 9 Serverless GPU Providers for AI Inference in 2026. Here's What I'd Actually Use
TL;DR If you're shipping AI inference and tired of babysitting GPUs, serverless is the way out. You deploy the model, the platform scales it from zero…
TensorCircuit-NG vs cuQuantum on H200: JIT compilation beats the "magic GPU library" assumption
NVIDIA cuQuantum has a strong reputation as the natural high-performance baseline for GPU quantum simulation. That reputation is understandable: cuQua…
GPU Incident at 3am: eBPF Tracing from Page to Root Cause in 60 Seconds
TL;DR 3am page: GPU training pipeline missed its SLA. Datadog shows 95% GPU utilization. nvidia-smi agrees. Everything looks green, but the job is 3x …
An AMD GPU Beat My Mac on Llama 8B. The Same GPU Lost on Phi-3.
I wrote a post yesterday about why GPUs barely help small text embeddings at batch=1. Different workload, same machines. This time I ran a local LLM i…
Your GPU Probably Isn't Helping Your Retrieval System
Most "just use a GPU" advice is wrong for how anyone actually runs small models. I spent yesterday benchmarking a 33M parameter embedding model across…
Best Local AI Models for Each VRAM Tier (4 GB to 80 GB) in 2026
This article was originally published on runaihome.com Every "best local AI model" article skips the question that actually matters: best for what VRA…
Тестируем выделенный L40S и vGPU на 16 ГБ по производительности (llama.cpp, ComfyUI)
Сегодня в интернете какой только нет информации об искусственном интеллекте или его применении в разных сферах. Можно сказать, что он уже плотно вошел…
Where Tensor-Parallel Inference Hits the NVLink Wall
Where tensor-parallel inference hits the NVLink wall 2026-05-31 · GPU / distributed systems Tensor parallelism splits each layer across GPUs, so every…
AMD Linux 7.2 Graphics & SteamOS VRR Drivers, NVIDIA Vera CPU Benchmarks
AMD Linux 7.2 Graphics & SteamOS VRR Drivers, NVIDIA Vera CPU Benchmarks Today's Highlights This week's top stories feature significant driver upd…
How to not Lose $500M via API Bills: Run Private AI for 100 Engineers Under $1 Million
Last week a company nobody can name spent $500 million in a single month on Anthropic's Claude API. Not $500K. Not $5M. Half a billion dollars. In one…
Used RTX 3090 Buying Guide for Local LLM in 2026
Cross-posted from Best GPU for LLM — visit the original for our VRAM calculator, GPU comparison table, and current Amazon pricing. The RTX 3090 is thr…
5090 vs 4090 for AI Workloads: Buy, Rent, or Validate in the Cloud?
Originally published at https://blog.runc.ai/5090-vs-4090/ . Key Takeaways RTX 5090 is the stronger flagship on paper, especially when your AI workflo…
CUDA 13.3 Lands, AI Writes Blackwell Kernels, & FP4 VRAM Optimization for LLMs
CUDA 13.3 Lands, AI Writes Blackwell Kernels, & FP4 VRAM Optimization for LLMs Today's Highlights NVIDIA releases CUDA Toolkit 13.3, bringing new …
FlashAttention CUDA Kernel, Strix Halo MOE Boost, & NVIDIA DLSS 4.5 Driver Update
FlashAttention CUDA Kernel, Strix Halo MOE Boost, & NVIDIA DLSS 4.5 Driver Update Today's Highlights This week, discover a deep dive into FlashAtt…
20 Years of GPUs in Numbers: How FLOPS & TDP Grew, and Who Led the NVIDIA vs AMD Race (open dataset, 13.5k GPUs)
We run a GPU spec catalog, and over a couple of years it grew into a database of 13,566 GPUs — from the GeForce 256 (1999) all the way to Blackwell an…
20 лет видеокарт в цифрах: как росли FLOPS и TDP и кто вёл в дуэли NVIDIA vs AMD (+ открытый датасет на 13 500 GPU)
Мы свели в одну базу характеристики 13 566 видеокарт — от GeForce 256 (1999) до Blackwell и MI355X (2025) — и посмотрели, как за 20 лет менялась индус…
How to Detect GPU Waste in a Kubernetes Cluster
GPU waste in Kubernetes does not announce itself. Your cluster shows healthy utilization. Your dashboards are green. But 20–40% of your GPU capacity i…
Why Your PyTorch Training Crawls on a Beefy GPU (And How to Fix It)
Last month I was helping a friend debug a training loop that was running at maybe 15% GPU utilization on an A100. Fifteen percent. On a card that cost…
RTX 5080 Undervolt Benchmarks, CGO-Free CUDA API Binding, & AMD GPU Compatibility Fix
RTX 5080 Undervolt Benchmarks, CGO-Free CUDA API Binding, & AMD GPU Compatibility Fix Today's Highlights Today's top GPU news features detailed un…