llama.cpp b9353 fixes HTTPS logging bug across platforms

llama.cpp, the open-source project for running large language models locally on consumer hardware, has released version b9353. This minor but important patch fixes a logging error in llama-server: when started with SSL key and certificate, the server was incorrectly logging that it listened on "http" instead of "https". While the actual encrypted connection was functioning correctly, the misleading log message could confuse administrators verifying their secure configurations. The fix ensures accurate reporting of TLS status.

The release continues llama.cpp's tradition of broad platform support. Builds are available for macOS (both Apple Silicon and Intel), iOS as XCFramework, Linux across x64, ARM64, and s390x CPUs—plus GPU-accelerated variants using Vulkan, ROCm 7.2, OpenVINO, and SYCL. Windows users get builds for x64 and ARM64 CPUs, plus CUDA 12/13, Vulkan, and HIP. Android ARM64 is also supported. The release also includes updated UI assets, though no further details on UI changes were provided. With 113k stars and 18.8k forks on GitHub, llama.cpp remains the go-to tool for developers running LLMs locally without cloud dependencies.