vLLM has released version 0.23.0, bringing substantial updates and optimizations. This release includes improvements to DeepSeek-V4, which now features a decoupled metadata structure and new attention kernels. Model Runner V2 has expanded its default support to include more dense models like Llama and Mistral. Additionally, the Rust frontend has been enhanced with new endpoints and tool parsers. Compatibility with Transformers v5 has also been addressed, ensuring broader model support. These updates make vLLM a more robust and versatile platform for developers.
Read originalLlama.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.
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.