b9751

ggml-org/llama.cppb9751Jun 21, 2026by github-actions[bot]same day as b9750

What changed since b9750

low risk

b9751 is a single bug-fix release correcting mtmd memory usage calculation, with no other changes from b9750.

Bug fixes

  • Corrected the memory usage calculation in the Multi-Modal (mtmd) module via a fix to mtmd_get_memory_usage.

Upgrade notes

This is a drop-in patch over b9750 with no API or config changes. Users relying on reported memory estimates for multimodal models should upgrade to get accurate values. Rebuild or re-download binaries as usual; no migration steps are required.

Analyzed Oct 31, 2026

Upgrading?

Release notes summary

This release fixes a bug in the Multi-Modal (mtmd) module where the memory usage calculation was incorrect. It provides the standard set of pre-built binaries for supported platforms.

Key Highlights

  • Fix memory usage calculation in Multi-Modal (mtmd) module
  • Release includes binaries for macOS, Linux, Android, Windows, and openEuler
  • Support for various hardware accelerators (CUDA, Vulkan, ROCm, etc.)

Release Notes (excerpt)

<details open> mtmd: fix mtmd_get_memory_usage (#24867) </details> **macOS/iOS:** - macOS Apple Silicon (arm64) - macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED - macOS Intel (x64) - iOS XCFramework **Linux:** - Ubuntu x64 (CPU) - Ubuntu arm64 (CPU) - Ubuntu s390x (CPU) - Ubuntu x64 (Vulkan) - Ubuntu arm64 (Vulkan) - Ubuntu x64 (ROCm 7.2) - Ubuntu x64 (OpenVINO) - Ubuntu x64 (SYCL FP32) - Ubuntu x64 (SYCL FP16) **Android:** - Android arm64 (CPU) **Windows:** - Windows x64 (CPU)…

Published by ggml-org on GitHub.

Read the full release notes

Related Repositories