ggml/llama.cpp releases: b10610

TL;DR

The ggml/llama.cpp project updated its codebase to shorten virtual device naming in CUDA and Metal, improving initialization processes for these platforms. These changes are crucial for enhancing the usability and performance of the project on GPU-based systems.

Detailed Summary

The ggml/llama.cpp project released updates (b10610) that include shortening virtual device naming in CUDA and Metal, and building device descriptions at initialization. These changes were assisted by DeepSeek-V4-Flash-0731 and are expected to improve the efficiency and clarity of device naming for GPU computations, impacting developers working with these frameworks.

Key Points

• • ggml : shorten virtual device naming in CUDA and Metal
• • ggml-metal : build device description at init
• • cont : naming