Models & Labs
Ollama 0.30 Enhances Performance and Model Support
Ollama Bloghigh confidence
Why it matters
- →Enhances performance on NVIDIA hardware by up to 20%, improving efficiency for developers.
- →Expands GPU acceleration to AMD and Intel devices, increasing accessibility for more users.
- →Broadens model compatibility, allowing more models to run out of the box, simplifying AI deployment.
Ollama has released version 0.30, bringing improved performance and expanded model support through GGUF compatibility. The update enhances performance on NVIDIA hardware by up to 20% and extends GPU acceleration to AMD and Intel devices using Vulkan. This version also increases compatibility with more models, including those from the GGUF ecosystem, allowing for easier deployment on various hardware. These improvements make it simpler for developers to utilize a broader range of models and hardware configurations.
Read originalMore in Models & Labs
Models & Labsmodels
Llama.cpp adds GLM-5.2 speculative decoding support
Llama.cpp's latest update introduces speculative decoding support for GLM-5.2, enhancing its capabilities with NextN/MTP features. This addition allows for more efficient tensor loading and context management, particularly benefiting models using the GLM_DSA architecture. The update also includes options for exporting models with or without the MTP feature, providing flexibility for developers. This release marks a step forward in optimizing model performance and adaptability, especially for those leveraging the GLM-5.2 framework.
llama.cpp Releases
Models & Labsmodels
Llama.cpp b10178 Release Adds Trace Logging
The b10178 release of llama.cpp enhances its server capabilities by adding trace logging for slot similarity checking, offering developers detailed insights into prompt cache slot selection processes. This update includes specifics on skip reasons and similarity calculations, which can aid in performance optimization. While no new model architectures are introduced, the release continues to support a wide array of platforms, such as macOS with KleidiAI, Ubuntu with ROCm 7.2, and Windows with CUDA 12 and 13. This makes llama.cpp a more versatile tool for developers working on different systems, reinforcing its position as a comprehensive inference runtime.