Models & Labs
llama.cpp b9534 release enhances Intel Vulkan support
llama.cpp Releaseshigh confidence
Why it matters
- →Enhances Intel Vulkan support with FWHT and shared memory reduction.
- →Addresses driver issues, improving stability on specific platforms.
- →Expands compatibility across diverse hardware configurations.
The b9534 release of llama.cpp brings significant updates, particularly for Intel users with the addition of FWHT support in Vulkan, which includes shared memory reduction. This release also addresses driver issues by disabling subgroup shuffle on MoltenVK AMD and the FWHT shader on Intel Windows. While some features like KleidiAI on macOS Apple Silicon are disabled, the update enhances compatibility across multiple platforms, including Ubuntu and Windows. These changes reflect llama.cpp's focus on optimizing performance and compatibility for a wide range of hardware.
Read originalMore from llama.cpp Releases
Open Sourcemodels
llama.cpp b9533 release expands platform support
The b9533 release of llama.cpp continues its focus on enhancing platform compatibility, though some features are notably absent. While macOS Apple Silicon users will find KleidiAI support disabled, the release introduces Vulkan support for both Ubuntu and Windows, and keeps CUDA support updated with new DLLs for Windows. The addition of ROCm 7.2 for Ubuntu x64 is particularly important for AMD GPU users, helping to close the gap with NVIDIA's CUDA. This update is more about refining existing capabilities and ensuring that llama.cpp runs smoothly across various environments, rather than unveiling new model architectures.
llama.cpp Releases
Open Sourcemodels
llama.cpp b9535 release expands platform support
The b9535 release of llama.cpp continues to broaden its platform compatibility, though some features remain unavailable. While macOS Apple Silicon users won't see KleidiAI support this time, the release introduces Vulkan support for both Ubuntu and Windows, offering more options for GPU utilization. The addition of ROCm 7.2 for Ubuntu x64 marks a significant step towards better AMD GPU support, helping to close the gap with NVIDIA's CUDA. However, features like SYCL support are still not enabled, indicating areas where development is ongoing. This release reflects llama.cpp's ongoing efforts to become a versatile inference runtime across a wide range of hardware setups.
llama.cpp Releases
Models & Labsmodels
llama.cpp b9536 release enhances OpenCL and platform support
The b9536 release of llama.cpp significantly boosts OpenCL performance, refining operations like get_rows, cpy, and concat for better efficiency. It now handles multiple workgroups in large rows, optimizing processing capabilities. Although KleidiAI support for macOS Apple Silicon is currently disabled, the release continues to cater to a wide array of platforms, including Windows, Linux, and Android, with specific enhancements for Vulkan and ROCm. These updates make llama.cpp more adaptable and efficient across various hardware setups, though some features remain inactive.
llama.cpp Releases
More in Models & Labs
© TechCrunch AIModels & Labsmodels
OpenAI introduces Lockdown Mode for ChatGPT
OpenAI has launched Lockdown Mode, a new feature aimed at enhancing security against prompt injection attacks in ChatGPT. This mode restricts certain functionalities like live web browsing and image retrieval, focusing on reducing the risk of sensitive data exposure. While it doesn't completely eliminate vulnerabilities, it offers an added layer of protection for users handling sensitive information. Currently, Lockdown Mode is being rolled out to ChatGPT Business accounts and select personal accounts, marking a step towards more secure AI interactions.
TechCrunch AI
© GitHub ChangelogModels & Labsmodels
GitHub Deprecates GPT-5.2 Models in Copilot
GitHub has deprecated the GPT-5.2 and GPT-5.2-Codex models across most Copilot experiences, signaling a shift in their AI offerings. While these models are no longer available for general use in Copilot Chat, inline edits, and code completions, they remain accessible for Copilot code review. This move requires users and administrators to update their workflows and enable alternative models through Copilot settings. The deprecation reflects GitHub's ongoing evolution of its AI tools, pushing users towards newer or more efficient models.
GitHub Changelog
© The AI AdvantageModels & Labsmodels
ChatGPT Memory Update and AI News Highlights
ChatGPT's memory update is a significant development, allowing the AI to retain information across sessions, which enhances user interaction by making conversations more coherent and personalized. This update is part of a broader trend of integrating AI more deeply into everyday tools, as seen with upcoming AI features in YouTube and the merger of Codex and ChatGPT apps. These changes reflect a growing emphasis on making AI more intuitive and useful in various contexts. The ability to remember past interactions could transform how users engage with AI, making it a more seamless part of daily digital life.
The AI Advantage