b9713

ggml-org/llama.cppb9713Jun 19, 2026by github-actions[bot]same day as b9712

What changed since b9712

medium risk

b9713 adds batching support to the multimodal CLI and introduces video tests, with no other changes noted.

New features

  • mtmd-cli now supports batching, allowing multiple multimodal inputs to be processed in a single invocation.
  • A new video test suite was added to broaden multimodal test coverage.

Improvements

  • Multimodal CLI workflows benefit from batched processing, reducing per-item overhead for multi-input runs.

Upgrade notes

This is a small incremental bump over b9712; the only functional delta is in the mtmd CLI and its tests, so existing llama.cpp server and library usage should be unaffected. If you script against mtmd-cli, verify your argument handling still behaves as expected with batching enabled. No config or model format migrations are indicated.

Analyzed Oct 24, 2026

Upgrading?

Release notes summary

Enhances the Multimodal CLI by adding batching capabilities and introduces new video tests for better coverage.

Key Highlights

  • Added batching support for mtmd-cli
  • Included video tests in the release
  • Improved CLI functionality for multimodal tasks

Release Notes (excerpt)

<details open> mtmd: add batching for mtmd-cli, add video tests (#24778) </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:**…

Published by ggml-org on GitHub.

Read the full release notes

Related Repositories