llama.cpp b11265 Release Improves Vulkan MoE Matmul Tile Selection

Core summary

One sentence to understand this update

llama.cpp has released version b11265, focusing on optimizing Vulkan's MoE-aware mat_mul_id tile selection for improved performance.

Impact & opportunity

What this could mean

Developers using llama.cpp can expect enhanced efficiency and performance for MoE model inference on Vulkan-enabled hardware.