llama.cpp version b9700 introduces updated SYCL support with renamed API flags: GGML_SYCL_SUPPORT_LEVEL_ZERO renamed to GGML_SYCL_SUPPORT_LEVEL_ZERO_API and GGML_SYCL_ENABLE_LEVEL_ZERO renamed to GGML_SYCL_USE_LEVEL_ZERO_API. The release includes binaries for macOS, Linux, Android, Windows, and openEuler across multiple architectures and hardware acceleration options, including Vulkan, ROCm, OpenVINO, and SYCL.