Skip to main content
← Back to news

llama.cpp b12198: proxy logs downgraded to trace, builds for CUDA 13.5, ROCm 10.0 and SYCL

Tools & releases
Source:llama.cpp
The llama.cpp server downgrades per-request proxy logs to the trace level; pre-releases for macOS, Linux (CPU, Vulkan, CUDA 12/13, ROCm, OpenVINO, SYCL), Windows, Android and Snapdragon with NPU. The local server engine keeps its weekly cadence.

Get the next local-AI briefing

Once a week, the top selection from iaLocale: articles, news and resources on local AI, and more.

After signing up you receive a confirmation email (double opt-in). Without confirmation we send nothing. No spam, we promise.