Models & Labs
Together AI partners with Moonshot AI for Kimi models
Together AI Bloghigh confidence
Why it matters
- →Provides developers with immediate access to advanced open-weight models.
- →Enhances scalability and flexibility for AI model deployment.
- →Challenges proprietary AI systems with competitive open-source alternatives.
Together AI has announced a strategic partnership with Moonshot AI to host and serve Moonshot's Kimi models, starting with the Kimi K3. This collaboration allows developers to access these large-scale open-weight models through Together AI's infrastructure, offering features like post-training and production-ready deployment. The Kimi K3 model, with its 2.8 trillion parameters and advanced architectural components, is designed for high-performance tasks such as coding and game development. This partnership aims to provide developers with scalable, open-source AI solutions that rival proprietary systems.
Read originalMore from Together AI Blog
More 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.