Maincode, an Australian AI company, built a custom inference engine in Rust for the AMD MI355X GPU that bypasses the ROCm runtime entirely, achieving lower overhead on critical operations like tensor-…
AMD opened pre-orders for its Ryzen AI Halo developer platform, a mini PC powered by the Ryzen AI Max+ "Strix Halo" processor with official Linux support and up to 128GB of unified memory for running …
Canonical announced plans to ship newer AMD ROCm versions as stable release updates (SRUs) for Ubuntu 26.04 LTS, addressing the current inclusion of the months-old ROCm 7.1. The company aims to delive…
Canonical and AMD have integrated the AMD ROCm AI/ML and HPC software stack directly into the Ubuntu 26.04 LTS archive, enabling users to install the libraries with a single `sudo apt install rocm` co…
AMD's ROCm platform now supports PyTorch, Ollama, LM Studio, and ComfyUI out of the box, enabling local AI workloads on AMD GPUs without the compatibility issues that plagued earlier versions. Users w…
AMD's ROCm (Radeon Open Compute platform) has reached production-ready maturity as an open-source alternative to NVIDIA's CUDA, now supporting LLM inference, fine-tuning, and image generation on AMD G…
The article provides a technical guide for running AI models like Flux Schnell (12B) and LLMs on a legacy AMD RX 580 (8GB) GPU using native Vulkan support, bypassing deprecated CUDA and ROCm ecosystem…
This article compares three dominant tools for local LLM inference in 2026: Ollama, llama.cpp, and vLLM. Ollama is recommended for personal, non-technical use due to its ease of setup, while llama.cpp…
PyTorch 2.12 introduces a new device-agnostic `torch.accelerator.Graph` API that unifies graph capture and replay across CUDA, XPU, and out-of-tree backends. The release delivers up to 100x faster bat…