Models & Labs
llama.cpp b9274 Release Fixes VRAM Leak
llama.cpp Releaseshigh confidence
Why it matters
- →Fixes a critical VRAM leak that caused server crashes.
- →Ensures proper resource management in Multi-Token Prediction models.
- →Enhances stability for developers using llama.cpp across platforms.
The b9274 release of llama.cpp resolves a significant VRAM leak issue that was causing server crashes. The problem stemmed from the destroy() function not freeing GPU-allocated resources in Multi-Token Prediction models during sleep cycles. By explicitly resetting speculative decoders and draft contexts, the update ensures proper resource management and prevents out-of-memory errors. This fix is crucial for developers relying on llama.cpp across multiple operating systems, including macOS, Linux, and Windows.
Read originalMore from llama.cpp Releases
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
Open Sourcemodels
llama.cpp b10175 Release Expands Platform Support
The latest b10175 release of llama.cpp continues its trend of broadening platform compatibility, making it a versatile tool for developers across different systems. Notably, this update includes support for ROCm 7.2 on Ubuntu x64, which is significant for AMD GPU users seeking alternatives to NVIDIA's CUDA. The release also maintains a wide array of builds for Windows, macOS, and Linux, ensuring that developers can leverage llama.cpp's capabilities regardless of their hardware setup. While there are no groundbreaking new features, the consistent expansion of platform support solidifies llama.cpp's position as a flexible inference runtime option.
