ggml/llama.cpp releases: b11010

TL;DR

The ggml/llama.cpp project released version b11010 to address a Vulkan bug related to NV graphics drivers, specifically with the argsort_large.comp function. This update is crucial for ensuring compatibility and stability across different hardware platforms, particularly on Apple Silicon Macs.

Detailed Summary

The ggml/llama.cpp project released version b11010, which includes a workaround for an NV bug related to the argsort_large.comp function in Vulkan. This update affects users of macOS Apple Silicon (arm64) and is available on the GitHub repository. The broader impact is improved functionality for users encountering specific issues with NVIDIA graphics cards on certain systems.

Key Points

• • Vulkan: Workaround NV bug with argsort_large.comp (#28975)
• • Website: <https://llama.app>
• • Attestations: <https://github.com/ggml-org/llama.cpp/attestations/48059150>