b10298

ggml-org/llama.cppb10298Aug 6, 2026by github-actions[bot]same day as b10297

What changed since b10297

medium risk

b10298 adds mtmd chunk save/load support and renames mtmd `_MAX` constants to `_COUNT`.

Breaking changes

  • mtmd public constants previously suffixed `_MAX` are renamed to `_COUNT`, so any downstream code referencing the old names will fail to compile.

New features

  • The mtmd multi-modal subsystem can now serialize and restore chunks via new save/load functions.
  • New tests were added covering the chunk save/load round-trip.

Improvements

  • Constant naming in mtmd was normalized from `_MAX` to `_COUNT` for clearer semantics.

Upgrade notes

This is a single-commit step over b10297, so the only practical concern is the mtmd constant rename: update any code or bindings that reference the old `_MAX` identifiers. If you only use the CLI or server binaries, no action is needed. The `/cors-proxy` fix from b10297 is retained.

Analyzed Oct 22, 2026

Upgrading?

Release notes summary

This release adds functionality to save and load chunks in the multi-modal (mtmd) system. It includes new tests to verify the functionality.

Key Highlights

  • Added chunk save/load functions for the mtmd system.
  • Added tests for the new chunk save/load functionality.
  • Renamed constants (e.g., `_MAX` to `_COUNT`).

Release Notes (excerpt)

<details open> mtmd: add chunk save/load function (#26645) * mtmd: add chunk save/load function * nits * add tests * rn _MAX --> _COUNT </details> **Website:** - <https://llama.app> **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)…

Published by ggml-org on GitHub.

Read the full release notes

Related Repositories