One of the initiatives launched by Intel in 2025 was LLM-Scaler as part of Project Battlematrix. The open-source LLM Scaler is a Docker-based solution for helping to deploy Generative AI "GenAI" workloads on Intel Battlemage graphics cards with frameworks like vLLM, ComfyUI, SGLang, and more. There continues to be routine new feature releases of LLM Scaler for broadening the large language models supported and other improvements...
Wild 0.8 is now available as this speedy linker focused on iterative development, a goal of incremental linking, and written in the Rust programming language...
For those shopping for an AI-ready mobile workstation with NVIDIA RTX PRO Blackwell graphics, the Lenovo ThinkPad P1 Gen 8 offers a lot of potential for developers, AI researchers, content creators, and others. This Linux-friendly mobile workstation is well built and aligns with ThinkPad P-Series expectations while being ready to be tasked with demanding workloads.
The upcoming Linux 6.20~7.0 kernel cycle will provide expanded GPU temperature reporting capabilities for Intel graphics cards. Additional temperature sensors will now be exposed under Linux with the Intel Xe driver using the hardware monitoring (HWMON) interface for easy consumption by different Linux user-space software...
A significant update to Burn was released today, the MIT and Apache 2.0 licensed tensor library and deep learning framework written in the Rust programming language. Burn 0.20 brings some low-level changes as it continues to strive to deliver high performance AI across the diverse hardware ecosystem...
Sent out today was the latest DRM-Misc-Next pull request of new material ahead of the next kernel cycle either Linux 6.20 or 7.0 depending upon what Linus Torvalds decides to call it...
Whisper.cpp as the open-source high performance inference project built around OpenAI's Whisper and from the same developers as Llama.cpp / GGML is out with a big new release. Whisper.cpp 1.8.3 is capable of delivering a 12x performance boost for systems with integrated AMD and Intel graphics...
Started last year was D7VK as a project bringing Direct3D 7 implemented over the Vulkan API for enjoying better performance and support for legacy Windows games on Linux, akin to DXVK and VKD3D-Proton for newer versions of Direct3D over Vulkan that is used by Valve's Steam Play (Proton). Back in December D7VK added a Direct3D 6 front-end for allowing even older game titles to be accelerated using the modern Vulkan API. Today D7VK 1.2 is out for furthering the D3D6 support...
Libvirt 12.0 released today as this open-source virtualization API for management across different virtualization technologies/hypervisors. With libvirt 12.0, improving Bhyve as the FreeBSD hypervisor was a big focus...
DeviceTree patches worked on recently allow for the mainline Linux kernel to run on the ASUS "Kommando" IPMI Expansion Card. This is interesting for opening up new possibilities for this external IPMI/BMC expansion card but too bad that less than three years after launching it's difficult to find...
The oVirt 4.5.7 open-source virtualization management platform released this week after not seeing any new releases in two years. While Red Hat had started the oVirt open-source project for which their Red Hat Virtualization platform is based, since they shifted that to maintenance mode to focus on the Red Hat OpenShift platform and stopped contributing to oVirt, it's been up to the open-source community to keep it going...
In late 2024 the folks at Raspberry Pi announced the Raspberry Pi AI HAT+ as an AI accelerator capable of 26 TOPS and costing $110 for pairing with Raspberry Pi single board computers. Today they announced the much more capable Raspberry Pi AI HAT+ 2 that can begin to take on some generative AI "GenAI" models...
Separate from the Mesa merge request talked about earlier today for new RADV code that can deliver 10x faster ray-tracing pipeline compilation for this open-source Radeon Vulkan driver, another merge request landed today in Mesa 26.0 that was also carried out by Valve contractor Natalie Vock. That second merge request now in Mesa 26.0 delivers some additional gains for at least some ray-tracing games on RDNA3 and RDNA4 GPUs...
Linux News