O Salto da AMD: Do ROCm 7.14 para o ROCm 10.0

 

O AMD ROCm 10.0 chega com ROCm.AI, saltando da versão 7.14 para um novo patamar. Descubra ganhos de performance, suporte a novas GPUs e como começar a desenvolver IA hoje.

AMD Lemonade 11.8: A IA Local de Alto Desempenho com DeepSeek V4 Flash no Strix Halo

AMD Lemonade 11.8: Rode o DeepSeek V4 Flash localmente em Strix Halo com facilidade. Servidor IA gratuito, privado e multi-hardware. Saiba como começar agora! 

A AMD Surpreende: O Novo Alvo "GFX1250-STRICT" no Compilador LLVM Acende Alertas

 

A AMD adiciona o misterioso alvo "gfx1250-strict" ao LLVM. Entenda o que é, para que serve e como impacta IA, HPC e o ecossistema open-source da AMD. (

A AMD ROCm acelera o passo: O ciclo de lançamentos de seis semanas e o futuro do desenvolvimento em IA

 

A AMD ROCm agora tem ciclo de lançamentos de seis semanas. Entenda o impacto, conheça o TheRock e prepare-se para o ROCm.AI. Leia o guia completo !

Lemonade 11.5: A AMD libera servidor local de IA com roteador inteligente paraa NPU, GPU e CPU

 

 A AMD lança Lemonade 11.5 com roteador inteligente para LLMs locais. Rode IA em NPU, GPU e CPU no Windows ou Linux. Gratuito, open-source e com total privacidade. Saiba tudo aqui! 

A AMD Acelera o Ecossistema de IA com o FastFlowLM, ROCm 7.14 e Lemonade 11.0

A AMD anuncia contratação do time FastFlowLM, lança ROCm 7.14, Lemonade 11.0 e GAIA 0.22. Entenda como o ecossistema open-source de IA local da AMD está se expandindo. 

O AMD ROCm 7.14 é lançado como versão oficial e já está pronto para o Advancing AI 2026

 

O AMD ROCm 7.14foi  lançado como uma versão oficial com TheRock, suporte a Ryzen AI 400 e ganhos de até 16% em IA. Saiba tudo sobre o lançamento e o Advancing AI 2026.

O Desafio de Rodar IA Localmente no Linux (e o que a Fedora nos Ensina)

 

Configurar IA local no Linux ainda é um desafio. Entenda os obstáculos, soluções práticas e como se preparar para o futuro do desenvolvimento de ML. 

Analysis of Ubuntu 26.04 LTS "Resolute Raccoon"

 

Ubuntu 26.04 LTS in-depth review: GNOME 50, APT 3.1, 10‑year support, and AI/ML readiness. Compare strengths, weaknesses, and find the right book.

The Ultimate Guide to AMD-Optimized Rocky Linux: Unlocking Enterprise AI & HPC Performance

Are you leaving enterprise AI performance on the table? Discover how AMD-optimized Rocky Linux can unlock peak HPC & LLM acceleration. Get expert analysis, a performance ROI guide, and insights into the future of data-center Linux. Download our free Executive Briefing.

AMD’s Linux 7.1 Update: Decoding GFX12.1, RDNA4, and the Future of High-Performance Computing

 

The current Linux 7.0 cycle saw AMD lay the initial groundwork for GFX12.0, the graphics IP powering the publicly available Radeon RX 9000 series (RDNA4). However, the real strategic value lies in what comes next. With the Linux 7.1 cycle, AMD is aggressively enabling GFX12.1, a yet-unreleased variant of the RDNA4 IP.

AMD’s Critical Linux 7.0 Patch Fixes RDNA4 Idle Power Drain After AI Workloads

 

AMD is rolling out a critical Linux kernel patch and new MES firmware to resolve severe idle power consumption issues on next-gen RDNA4 (Radeon RX 9000 series) GPUs. Following workloads like AI inference with Llama.cpp, these graphics cards were stuck at 100% utilization, leading to abnormal energy use. Here is the technical breakdown of the fix heading to Linux 7.0.

The Paradigm Shift: Running LLMs on AMD Ryzen AI NPUs with Linux

 

Unlock the full potential of AMD Ryzen AI NPUs on Linux. Our in-depth guide covers the revolutionary Lemonade 10.0 and FastFlowLM integration, enabling efficient LLM inference. Learn about kernel requirements, supported Ryzen AI 300/400 hardware, and how this shifts the paradigm for open-source AI development on edge devices.

AMD Quietly Unlocks GPU Performance Analysis: ROCprof Trace Decoder Goes Open-Source

 

AMD has quietly open-sourced the ROCprof Trace Decoder, a critical component for GPU performance analysis. This MIT-licensed tool unlocks hardware-level thread tracing on Instinct and Radeon GPUs, providing kernel developers with unprecedented visibility into wave execution. 

The Linux Kernel's Colossus: How the AMDGPU Driver Surpassed Six Million Lines of Code

 

Explore the exponential growth of the AMDGPU driver in Linux Kernel 7.0, now exceeding six million lines of code. This deep-dive analyzes the architectural reasons behind this expansion, the role of auto-generated headers, and what this dominance means for the open-source ecosystem and enterprise computing.

Master AMD's Peak Tops Limiter (PTL) for Superior AI/ML Power & Thermal Management

 

Discover how AMD's new Peak Tops Limiter (PTL) in the AMDGPU/AMDKFD Linux drivers enables granular control over Instinct accelerator computational throughput. This in-depth guide covers sysfs controls, ROCm APIs, and kernel parameters for optimizing power efficiency and thermal budgets in high-performance computing and AI workloads. Learn implementation strategies for data centers and research labs.

Decoding AMD’s LLVM GFX13 Commit: The First Official Glimpse of RDNA5 Architecture

 

The LLVM 23 Git codebase now includes the initial AMDGPU GFX13 target, signaling development for AMD's next-gen RDNA5 graphics architecture. This article provides a deep technical analysis of GFX13's implications, its evolution from GFX12/RDNA4, and what it means for future GPU programming, high-performance computing, and competitive benchmarking against NVIDIA. Read our expert breakdown.

AMD ROCm 7.2.0 Launch: Official RDNA4 & RDNA3 GPU Support, New Tools, and Performance Optimizations

 

AMD's ROCm 7.2.0 is now officially available, expanding open-source GPU compute support to new RDNA4 graphics cards like the Radeon AI PRO R9600D and RX 9060 XT LP, while finally adding RDNA3 support. Discover the performance enhancements, new HIP APIs, and the beta launch of the ROCm Optiq visualization platform in this comprehensive release analysis.

PyTorch 2.10 Release: A Comprehensive Guide to GPU Acceleration, Performance Optimizations, and Deep Learning Enhancements

 

PyTorch 2.10 introduces major upgrades for Intel, AMD, and NVIDIA GPU acceleration, Python 3.14 compatibility, and advanced kernel optimizations. Explore performance benchmarks, key features, and enterprise AI implications in this detailed technical analysis. 

AMDGPU & AMDKFD Linux Driver Patches: A Deep Dive into RDNA 4 Prep & 340MHz HDMI Boost for Linux 6.20~7.0

 

Explore the latest AMDGPU & AMDKFD Linux kernel patches for Linux 6.20~7.0. Dive deep into RDNA 3.5/4.0 (GFX12.1) support, SMU 15 updates, 340MHz HDMI clock fixes for 4K/8K displays, and ARM64 server optimizations. A must-read for Linux sysadmins, PC builders, and HPC developers.