The ggml‑org team released llama.cpp version b11413 on Oct 5 2026. The update adds a Vulkan implementation of sparse flash attention that works with quantized key/value tensors. The change is described as "sparse flash attention for quantized K/V" and is aimed at GPU‑accelerated inference. The release also lists many platform builds, from macOS Apple Silicon to Windows CUDA and Vulkan.
Why it matters
Developers can now run quantized models faster on GPUs that support Vulkan, lowering compute cost for edge devices.
