ggml/llama.cpp releases: b10865

TL;DR

The ggml/llama.cpp project reverted a commit to restore `prop.integrated` on HIP builds, addressing potential issues with CUDA and HIP compatibility. This change is important for maintaining the library's functionality across different hardware platforms.

Detailed Summary

The ggml/llama.cpp project reverted a commit related to CUDA settings on HIP builds, addressing potential issues in the codebase. This update involves developers working on optimizing GPU support for machine learning models. The broader impact includes improved compatibility and stability across different hardware platforms, benefiting users of the llama.cpp framework who rely on both NVIDIA and AMD GPUs.

Key Points

• • Reverts commit c7d8722922a2599dc4d77f8808d8e6c2fde5e7a2
• • Website: <https://llama.app>
• • Attestations: <https://github.com/ggml-org/llama.cpp/attestations/46002046>