# llama.cpp reuses Vulkan descriptors during model inference

The Vulkan backend gains a change to resource setup for local inference. Retrospective brief for 07:00–07:59 UTC on 29 September 2026.

## Vulkan descriptor sets are reused when bindings stay constant

The llama.cpp b11247 development build reuses Vulkan descriptor sets when their bindings are unchanged and updates buffer-destruction tracking. This is a backend change in the local model runtime, relevant to developers building or testing its Vulkan inference path. GitHub marks this build as a prerelease; the release notes do not provide a quantified speedup. 

[ggml-org/llama.cpp b11247 release notes](https://github.com/ggml-org/llama.cpp/releases/tag/b11247)