ggml/llama.cpp releases: b10794

TL;DR

The ggml/llama.cpp project released a new version that includes a SYCL refactoring to enable MKL-based floating-point arithmetic globally. This update is significant as it enhances the project's computational efficiency, particularly for Apple Silicon platforms.

Detailed Summary

The ggml/llama.cpp project released a new version with a SYCL refactor to enable MKL for global variables, as part of issue #26863. This update is relevant for users on macOS Apple Silicon (arm64) and those interested in leveraging MKL for improved performance. The broader impact includes enhanced computational efficiency for machine learning tasks on specific hardware configurations.

Key Points

• • Refactor GGML_SYCL_ENABLE_MKL_FA to global var (#26863)
• • Website: <https://llama.app>
• • macOS/iOS support for Apple Silicon (arm64)