Models & Labs
llama.cpp releases version 0.3.0
llama.cpp Releaseshigh confidence
Why it matters
- →Expands platform support, making llama.cpp more versatile for developers.
- →Enhances compatibility with new architectures like Apple Silicon and Vulkan.
- →Strengthens llama.cpp's position as a tool for diverse computing environments.
llama.cpp has released version 0.3.0, bringing updates to its platform support and functionality. This version includes enhancements for macOS, Linux, Windows, and openEuler, with notable support for CUDA 13 on Windows and ROCm 7.14 on Ubuntu. The update aims to improve compatibility across various architectures, including Apple Silicon and Vulkan. While no new features are introduced, the release strengthens llama.cpp's utility for developers working in diverse computing environments.
Read originalMore from llama.cpp Releases
Models & Labsmodels
llama.cpp b10618 Release Enhances Parsing
The b10618 release of llama.cpp tackles a crucial parsing issue, specifically improving the handling of hyphens in character classes. This update ensures that generated tool-call grammars are parsed correctly, enhancing the software's reliability. With new parser and integration tests included, the release verifies these improvements effectively. While it doesn't introduce major new features, this update strengthens llama.cpp's core functionality, making it more dependable for developers working on different operating systems and hardware configurations.
llama.cpp Releases
Models & Labsmodels
llama.cpp b10620 Release Expands Platform Support
The b10620 release of llama.cpp marks another step in broadening its platform reach, now supporting systems like Ubuntu with Vulkan and ROCm 7.14, alongside Windows with CUDA 13. This update underscores llama.cpp's adaptability, making it a go-to tool for developers working across various hardware configurations, from macOS Apple Silicon to Windows arm64. While the release doesn't introduce new groundbreaking features, it reinforces llama.cpp's role as a flexible inference runtime. By ensuring compatibility with more systems, llama.cpp becomes increasingly accessible to developers, allowing them to leverage its capabilities regardless of their hardware setup.
llama.cpp Releases
Models & Labsmodels
llama.cpp b10622 release addresses OOM crash
The latest b10622 release of llama.cpp addresses a critical issue that caused out-of-memory crashes on memory-constrained devices like iOS. By implementing a null-check for the Metal buffer allocation, the update prevents hard crashes and instead logs errors for better diagnostics. This change is particularly significant for developers working with Metal on Apple devices, ensuring more stable performance when memory limits are reached. The update doesn't introduce new features but enhances reliability, making it a crucial fix for those deploying models on constrained hardware.
llama.cpp Releases
More in Models & Labs
© NVIDIA BlogModels & Labsmodels
NVIDIA Unveils RTX Spark for Next-Gen Gaming
NVIDIA is set to revolutionize PC gaming with the introduction of RTX Spark, a platform that integrates personal AI agents, advanced content creation, and high-performance gaming. Announced at Gamescom, RTX Spark will support major titles from publishers like Electronic Arts and Ubisoft, ensuring seamless gameplay with enhanced visual fidelity. The platform also incorporates sophisticated anti-cheat technologies, crucial for maintaining fair play in multiplayer games. With its launch this fall, RTX Spark promises to elevate the gaming experience by combining NVIDIA's RTX technologies with Windows devices, offering gamers unprecedented levels of detail and performance.
NVIDIA Blog
© Hugging Face BlogModels & Labsmodels
Granite 4.2 LLMs Introduced by IBM and Hugging Face
Granite 4.2 marks a significant step forward in reasoning-focused language models, offering three sizes—3B, 8B, and 30B—all built on a dense, decoder-only architecture. These models are pre-trained on a massive 15 trillion tokens and feature a unique five-phase training strategy that extends the context window to 512K tokens. Notably, the 8B and 30B models undergo agentic reinforcement learning, enabling them to operate as agents in real environments, such as editing code and searching the web. This release under the Apache 2.0 license makes advanced reasoning capabilities more accessible to developers, with native tool calling and OpenAI-compatible endpoints enhancing usability.
Hugging Face Blog
© TechCrunch AIModels & Labsmodels
OpenAI's Jalapeño Chip Outperforms in Benchmarks
OpenAI's Jalapeño chip has demonstrated significant performance improvements in inference tasks, surpassing current state-of-the-art processors in benchmarks. At the Hot Chips conference, OpenAI revealed that Jalapeño offers more tokens per user and higher throughput per kilowatt, indicating its efficiency and speed. Developed in collaboration with Broadcom, Jalapeño aims to minimize data movement and communication delays, addressing common bottlenecks in AI inference. While the chip shows promise, its full deployment is expected by 2027, leaving room for competitors to advance in the meantime.
TechCrunch AI