ggml_rope_set_offset

This release updates the OpenVINO backend to version 2026.3.1, adds support for Whisper.cpp and Qwen3.5 on NPU, and introduces new operations. It also includes significant improvements to static shape handling, token-count independence, and chunked prefill for better performance and accuracy.

llama.cpp 0.3.0 introduces multimodal capabilities with the dots3-note model and MTP support for GLM-4.5-Air, alongside significant updates to ggml and core model handling.

This release includes a minor update to the mtmd component, utilizing ggml_rope_set_offset for improved functionality. It also provides pre-compiled binaries for various platforms and configurations.

Introduced `ggml_rope_set_offset` with expanded backend support including Metal, CUDA, and Vulkan. This release also provides updated pre-compiled binaries for various platforms and hardware configurations.