Linux Graphics & Gaming News
Ollama has recently released version 0.40.9, introducing significant new capabilities for local large language models. This update enables speech generation using Phonon, exclusively on Apple Silicon....
Read more →Ollama recently released version 0.40.5, introducing support for NVIDIA's Nemotron 3.5 Super and Nemotron 3.5 Bolt vision-language models (VLMs). Nemotron 3.5 Super is a 120-billion-parameter hybrid M...
Read more →Mesa has recently expanded its Neural Processing Unit (NPU) capabilities by integrating support for YOLOX models via PyTorch. Open-source developer Tomeu Vizoso has been instrumental in advancing thes...
Read more →Rust-GPU v0.10.0 was released, updating its toolchain to nightly-2026-07-03 (rustc 1.98.0). This release introduces support for the VK_KHR_cooperative_matrix Vulkan extension, enabling efficient matri...
Read more →Ollama v0.35.0 was released today, introducing support for decision models through its new /v1/systemone API. This feature, based on TypeSafe’s Jev API, enables models to return choices, probabilities...
Read more →Ollama v0.34.4 was released today, bringing several enhancements for local large language model inference. The update improves structured outputs on thinking models, making them faster and more reliab...
Read more →Ollama has released v0.40.0-rc0, a new release candidate that significantly enhances performance for local large language models on Apple hardware. Posted recently, this update enables the MLX runtime...
Read more →Ollama, the tool for running large language models (LLMs) locally, has released version v0.34.4-rc0 today. This release candidate addresses intermittent "model not found" errors, aiming to improve the...
Read more →AMD GPUOpen recently detailed MiniDXNN v0.4.0, an update to its interactive neural texture compression tool, bringing significant enhancements for DirectX 12 developers. The new version introduces sup...
Read more →Ollama released v0.32.10-rc1, a new release candidate, introducing several enhancements. A notable change is the default repeat penalty for models that do not explicitly set this parameter; it now def...
Read more →Vulkan 1.4.356 was released today, July 4, 2026. This update introduces a single new extension, Microscaling MX data types.">VK_EXT_shader_ocp_microscaling_types. This extension enables Vulkan to utilize the Open Compute Project'...
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 →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 →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 →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 →