Open Source
JetBrains Releases Mellum2 12B MoE Open-source
Lev Selectorhigh confidence
Why it matters
- →Promotes open-source collaboration and innovation.
- →Provides a high-performance model for diverse AI applications.
- →Encourages efficient use of computational resources.
JetBrains has released Mellum2, a 12 billion parameter mixture of experts (MoE) model, as an open-source project. This model leverages the MoE architecture to efficiently manage computational resources while maintaining high performance. The open-source release aims to foster innovation and collaboration within the AI community.
Read originalMore from Lev Selector
© Lev SelectorModels & Labsmodels
Microsoft Launches Project Solara Chip-to-Cloud Platform
Microsoft has introduced Project Solara, a new chip-to-cloud platform aimed at enhancing AI integration.
Lev Selector
© Lev SelectorModels & Labsmodels
NVIDIA Unveils RTX Spark Laptops and DGX Stations
NVIDIA has announced new RTX Spark laptops and DGX Stations for running large AI models locally.
Lev Selector
© Lev SelectorModels & Labsmodels
MiniMax Releases M3 Multimodal Model
MiniMax has launched the M3 Multimodal Model, enhancing capabilities across multiple data types.
Lev Selector
More in Open Source
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
Open Sourcemodels
llama.cpp b9537 Release Expands Platform Support
The b9537 release of llama.cpp continues its trend of broadening platform compatibility, though with some notable exceptions. While macOS Apple Silicon users see KleidiAI support disabled, the release strengthens its Linux offerings with ROCm 7.2 and Vulkan support across multiple architectures. Windows users benefit from CUDA 12 and 13 DLLs, enhancing GPU performance options. Despite some disabled features, this update demonstrates llama.cpp's commitment to being a versatile inference runtime across diverse systems, though it remains a work in progress for certain configurations.
llama.cpp Releases