#ROCm

46 related articles

Jul 28, 2026·3 min

ncnn Vulkan Cross-Platform Edge Inference in Practice: Solving the GPU Fragmentation Deployment Challenge

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.

Jul 28, 2026·3 min

AMD CDNA5 Architecture Deep Dive: Technical Evolution and the AI Computing Competition Landscape

Deep analysis of AMD's CDNA5 architecture covering Chiplet packaging upgrades, HBM memory evolution, and low-precision compute optimization, examining how AMD challenges NVIDIA's AI chip dominance.

Jul 27, 2026·2 min

RX 9060 XT vs RTX 5060 Ti: Which GPU to Pick for Local AI?

RX 9060 XT vs RTX 5060 Ti — both 16GB VRAM, but which is better for local AI? We compare CUDA ecosystem, ROCm compatibility, LLM inference, and real-world usability.

Jul 27, 2026·2 min

RX 9060 XT vs RTX 5060 Ti: How to Choose a GPU for Local AI

RX 9060 XT vs RTX 5060 Ti both offer 16GB VRAM — which is better for local AI inference? A full comparison of CUDA ecosystem, ROCm compatibility, LLM performance, and real-world usability.

Jul 26, 2026·3 min

Rust and Mojo Are Quietly Replacing Python's Low-Level Engine

Python tops the language rankings again, but AI teams are quietly swapping its internals for Rust and Mojo. A look at Python's speed and GIL pains, the two-language problem, and the rise of Rust tooling and Mojo on GPUs.

Jul 24, 2026·4 min

Dify Local Deployment Guide: One-Click Private AI Platform with Docker

Step-by-step guide to deploying Dify AI platform locally with Docker. Covers Linux, Windows, macOS setup, docker compose launch, and first-time initialization in under 30 minutes.

Jul 22, 2026·2 min

Agent A1 Open Source: 35B MoE Local Inference Speed Test & Deployment Guide

Agent A1 is a 35B MoE open-source model from Shanghai's Intern Science, activating only 3B params. Hits 95 tok/s on M4 Mac Studio. Supports 256K context, tool calling, and free local deployment via Ollama.

transcribe.cpp: A Unified Speech Recog…

Jul 21, 2026·2 min

transcribe.cpp: A Unified Speech Recognition Engine Built on ggml, Supporting 16+ Model Families

transcribe.cpp is an open-source ggml-based speech recognition engine supporting 16+ model families in a single C++ codebase — lightweight, cross-platform, and quantization-ready for local STT.

Jul 19, 2026·4 min

AMD Ryzen AI Halo Real-World Test: Can a Non-Programmer Use Local AI to Write Code?

A non-programmer tests AMD Ryzen AI Halo by deploying local AI models to tackle a real dev task. After testing Ollama and Qwen3, the verdict: AI amplifies developers, it doesn't replace them.

Jul 19, 2026·2 min

6-Day Open Source AI Agent: Natural Language-Driven Android Automation Testing

Veta is an open source AI testing agent: just describe your test goal in natural language and it autonomously plans, executes, verifies, and reports Android test results — no scripts needed.

Jul 16, 2026·2 min

llama.cpp Milestone: The Open-Source Evolution of Local LLM Inference

llama.cpp hits a new milestone, growing from a solo hobby project into core local AI inference infrastructure. Explore its iteration speed, GGUF quantization, and how AI coding agents are reshaping open-source development.

4 Alternatives for Running CUDA on Non…

Jul 15, 2026·3 min

4 Alternatives for Running CUDA on Non-NVIDIA Hardware: A Comparative Guide

A deep dive into running CUDA on non-NVIDIA hardware (AMD, Intel): comparing ROCm/HIP, ZLUDA, SYCL/oneAPI, and OpenCL across principles, use cases, and limitations.

Building an eGPU for Local LLM on a $1…

Jul 14, 2026·2 min

Building an eGPU for Local LLM on a $1,000 Budget: A Practical Buying and Setup Guide

Building an eGPU for local LLMs on a $1,000 budget? This guide covers GPU selection, dock costs, RTX 3090 vs 3060 value, and top tools like Ollama and llama.cpp.

The Circular Financing Trap in Nvidia'…

Jul 12, 2026·4 min

The Circular Financing Trap in Nvidia's Ecosystem: The Capital Undercurrents Behind the GPU Boom

An in-depth look at the circular financing model among Nvidia, CoreWeave, and Nebius—where suppliers double as investors, capital self-reinforces, and valuation bubbles and systemic risk lurk behind the AI infrastructure boom.

Jul 12, 2026·4 min

E2AM: An Open-Source Tool to Quantify AI Training Energy Consumption and Carbon Emissions in Two Lines of Code

E2AM is a Green AI open-source tool that monitors AI model training energy use, carbon emissions, and accuracy-per-joule metrics in just two lines of code. Supports PyTorch and Hugging Face, runs locally with no server needed.

Jul 12, 2026·3 min

DeepSeek-V4 Flash RL Training Successfully Ported to AMD MI355X GPU: A Complete Breakdown

The Miles team and AMD announce the full port of DeepSeek-V4 Flash RL training to AMD Instinct MI355X GPUs on ROCm, boosting AIME pass@1 from 0.39 to 0.49—a milestone for compute ecosystem diversity.

Jul 12, 2026·4 min

AMD Ryzen AI Halo Hands-On: Can x86 Architecture Challenge NVIDIA's DGX Spark?

In-depth review of the AMD Ryzen AI Halo mini AI box: powered by the Ryzen AI Max Plus 395 (Strix Halo) chip with 128GB unified memory, priced at $4,000. Compared against NVIDIA's DGX Spark across token generation, prefill speed, and x86 advantages.

Jul 11, 2026·3 min

The Software Compounding Effect: The Real Deciding Factor in AI Infrastructure Competition

Beyond the GPU arms race, software is becoming AI infrastructure's true compounding engine. A deep dive into optimization stacking, the CUDA ecosystem moat, and how open source scales individual breakthroughs into community wealth.

Jul 11, 2026·4 min

Demystifying Unified Memory Architecture: How Mini PCs Run 70B Large Models

Why can a mini PC with unified memory run a 70B model while an RTX 4090 can't? A deep dive into the VRAM wall and unified memory architecture for smarter local AI hardware choices.

Jul 11, 2026·5 min

Why Did Ollama Rise So Fast? Decoding the Success of a Local LLM Tool

How did Ollama grow from a niche open-source project into developers' default choice for running local LLMs? This article breaks down its rise across product design, technical strategy, and ecosystem building.