A developer successfully ran local AI inference on an AMD RX 580 (2017 GPU) using the Vulkan backend of llama.cpp and stable-diffusion.cpp, bypassing the lack of CUDA or ROCm support. The setup achiev…
AMD-backed Lemonade AI server released v10.8 with Model Context Protocol (MCP) server integration, enabling MCP-compatible clients like GitHub Copilot and Claude Desktop to use local AI models as tool…
VLLM, a model-serving engine for large language models, introduced a small op-level IR to resolve the tension between acting as a compiler target and a hand-tuned kernel dispatcher. The IR allows vLLM…
Kog AI achieved over 3,000 output tokens per second per request for an FP16 2B model on a single 8× MI300X node using a monokernel that eliminates per-token kernel launches. The technique collapses th…
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…