Linux Graphics & Gaming News
Ollama has released version 0.23.1, introducing Gemma 4 Multi-token Processing (MTP) speculative decoding for its MLX runner. This update, primarily benefiting macOS users with Apple Silicon, can prov...
Read more →The OpenVX Working Group at Khronos today released two new extensions, Target Kernel and Node Command, aimed at improving computer vision and AI applications on modern heterogeneous Systems on a Chip....
Read more →Ollama v0.23.0 was released today, introducing official support for the Claude Desktop application. This integration allows users to run both Claude Cowork and Claude Code directly within the Claude D...
Read more →Ollama has released v0.22.1-rc1, bringing notable enhancements for local AI model execution. Key updates include the addition of NVIDIA TensorRT Model Optimizer import support, which allows for levera...
Read more →Ollama released version 0.21.1 recently, introducing the Kimi CLI for local AI model execution. Users can now launch the Kimi CLI via Ollama, which "excels at long horizon agentic execution tasks thro...
Read more →Collabora announced on April 17, 2026, the integration of BitNet-style ternary Large Language Model (LLM) inference into ExecuTorch. This implementation leverages ExecuTorch's Vulkan backend to enable...
Read more →Ollama released version 0.20.6 today, focusing on enhancements for local AI deployments. The update notably improves Gemma 4 tool calling capabilities, incorporating Google's latest post-launch fixes ...
Read more →MZLA Technologies, the for-profit subsidiary of the Mozilla Foundation, recently announced Thunderbolt, a new open-source AI client. Developed with support from a Mozilla grant, Thunderbolt is designe...
Read more →Ollama v0.21.0 was released today, introducing the Hermes Agent for enhanced local AI workflows. This integration allows users to deploy Nous Research's self-improving AI agent via the 'ollama launch ...
Read more →Today, the Simple DirectMedia Layer (SDL) project, a widely used cross-platform development library for games and a core component of the Steam Runtime, implemented a new policy. This policy explicitl...
Read more →Ollama, a framework designed for running large language models locally, recently released version 0.20.7. This update brings key improvements for Linux users, especially those utilizing AMD GPUs for t...
Read more →Ollama announced its v0.20.8-rc0 pre-release candidate recently, introducing several updates with a key focus on improved hardware support. For Linux users, this version notably updates its AMD ROCm i...
Read more →AMD GPUOpen today announced the release of MiniDXNN, a new native HLSL and DirectX 12 library designed for machine learning inference. This library specifically targets rapid Multi-Layer Perceptron (M...
Read more →Ollama v0.20.5 was released on April 9, 2026, introducing significant new features for local AI model interaction and performance. The update includes the OpenClaw channel setup, which allows users to...
Read more →AMD GPUOpen recently introduced MinDXNN, a new native HLSL and DirectX 12 library designed for lightning-fast Multi-Layer Perceptron (MLP) inference. The library targets AMD Radeon RX 9000 series grap...
Read more →The Linux 7.0 kernel, currently nearing its stable release, today gained support for three additional standardized keycodes designed for AI agent interactions on future PC hardware. This merge expands...
Read more →Intel Arc Pro B70, a Battlemage G31 graphics card featuring 32 Xe cores and 32GB of GDDR6 memory, received initial Linux benchmarks this week from Phoronix. The card was announced last month, and Phor...
Read more →Collabora's multimedia engineering team recently detailed significant enhancements to GStreamer 1.28. These updates, contributed by 16 individuals, include major improvements across the multimedia sta...
Read more →Ollama recently released version 0.20.0, which introduces support for the Gemma 4 series of large language models. This includes "Effective 2B (E2B)", "Effective 4B (E4B)", "26B (Mixture of Experts mo...
Read more →Ollama, the local AI framework, released version 0.19.0 today, March 30, 2026. This update introduces a new web search plugin for its 'ollama launch pi' command, enabling direct web search capabilitie...
Read more →AMD recently released GAIA 0.17, an update to its AI agent framework designed specifically for Ryzen AI hardware. This new version introduces Agent UI, a privacy-first web application for managing and...
Read more →Ollama released version 0.18.3 yesterday, introducing direct integration with Microsoft Visual Studio Code through GitHub Copilot. This update allows developers to select and utilize any local or clou...
Read more →Ollama has released version 0.18.2 today, introducing performance improvements and fixes for its integration with OpenClaw. A key update in this release is the enhanced speed of local AI code generati...
Read more →Google's agentic AI code review service, Sashiko, has expanded its monitoring to include submissions on the Rust-For-Linux mailing list. Unveiled by Google engineers a few days ago, Sashiko is powered...
Read more →Ollama v0.18.1 was released, introducing new web search and web fetch plugins specifically for OpenClaw. This update allows Ollama's language models, whether local or cloud-based, to search the web fo...
Read more →AMD has released LLVM and MLIR.">MLIR-AIE v1.3 today, advancing its compiler toolchain for AMD AI Engine devices, including Ryzen AI NPUs. This update introduces the AIECC C++ compiler, designed to facilitate the dep...
Read more →Ollama version 0.18.0 was released today, bringing significant performance improvements and new integration capabilities for AI model usage. The update enhances the speed of OpenClaw and Ollama's clou...
Read more →An independently developed open-source Linux kernel module called GreenBoost has been reported today. It aims to augment the dedicated video memory (vRAM) on NVIDIA discrete GPUs by utilizing both sys...
Read more →NVIDIA's recently released CUDA 13.2 now provides official support for Red Hat Enterprise Linux (RHEL) compatible distributions, including AlmaLinux. This update means that NVIDIA CUDA packages can be...
Read more →AMD recently released GAIA 0.16, its open-source framework for building AI agents that execute locally on Ryzen AI hardware. This new version introduces a C++17 agent framework, enabling developers to...
Read more →Ollama v0.17.5 was released today, introducing support for the Qwen 3.5 small model series, now available in 0.8B, 2B, 4B, and 9B parameter sizes. This update addresses several critical issues, includ...
Read more →Phoronix has published new Linux benchmarks detailing the Intel Rendering Toolkit and OpenVINO AI performance on Intel's Panther Lake processors. The testing focused on the Core Ultra X7 358H, which f...
Read more →The February 2026 edition of Steam Next Fest recently began, offering demos for a range of upcoming games. The event, hosted by Valve, aims to raise awareness for new titles, allowing players to sampl...
Read more →Linux block maintainer and IO_uring lead developer Jens Axboe recently utilized Claude AI to debug performance issues within the AHCI/SCSI code when using IO_uring. This collaboration led to the devel...
Read more →Ollama released version 0.16.0 yesterday, enhancing its local large language model ecosystem with new models and a simplified command-line interface. The update introduces GLM-5, a 744 billion paramet...
Read more →The extensive set of Linux kernel graphics and display driver updates, known as Direct Rendering Manager or DRM, were merged today, February 12, 2026, for the upcoming Linux 7.0 kernel. This update pa...
Read more →Ollama 0.15.0 was released today, introducing the new "ollama launch" command. This command allows users to directly integrate Ollama's models with various large language models, including Claude Code...
Read more →Ollama released version 0.14.3 three days ago, introducing several new large language models and text-to-image capabilities. Key additions include Z-Image Turbo, a 6 billion parameter text-to-image mo...
Read more →PyTorch 2.10 was released today, January 22, 2026, as the latest feature update to the deep learning library. This new release continues to improve support for Intel GPUs and the AMD ROCm compute stac...
Read more →Ollama released version 0.14.2 today, January 19, 2026, a minor update following the experimental image generation models in 0.14.1. The highlight of this release is the introduction of "TranslateGemm...
Read more →Ollama v0.14.1 was released today, January 18, 2026, bringing experimental support for image generation models. This new functionality is available for Linux systems configured with CUDA-compatible GP...
Read more →The open-source ZLUDA project announced its progress from the fourth quarter of 2025 today, January 14, 2026. ZLUDA, which aims to enable unmodified CUDA applications to run on non-NVIDIA GPUs, now bo...
Read more →Phoronix has published a benchmark comparison evaluating the Dell Pro Max with NVIDIA GB10 against AMD's Ryzen AI Max+ 395 "Strix Halo" within a Framework Desktop SFF PC. The Dell Pro Max, which integ...
Read more →AMD today announced its initial consumer product lineup for 2026 following Lisa Su's keynote at CES 2026. The company unveiled the Ryzen AI 400 series processors, alongside new Ryzen 7 9850X3D 3D V-Ca...
Read more →Intel's Video Processing Library (libvpl) recently received an update, reaching version 2.16. The most notable addition in this release is the integration of experimental APIs designed for AI-assisted...
Read more →Canonical today announced plans to package and distribute the AMD ROCm software stack directly within the Ubuntu 26.04 LTS repositories. This integration, set for next year's long-term support release...
Read more →Ollama has recently released version 0.13.2-rc2, bringing several updates focused on AI model performance and GPU compatibility. A significant change is the default enablement of flash attention for v...
Read more →AMD GPUOpen recently announced AMD Schola v2, a significant update to its open-source reinforcement learning (RL) plugin for Unreal Engine 5. Schola v2 is described as a "next-generation reinforcement...
Read more →Intel's open-source driver support for its Gaudi 3 AI accelerator was rejected from the Linux 6.19 kernel mainline merge window yesterday. Intel had submitted the substantial patch set last night, aim...
Read more →