b9610

ggml-org/llama.cppb9610Jun 12, 2026by github-actions[bot]same day as b9608

What changed since b9608

low risk

b9610 is a routine ggml submodule sync with no documented functional changes beyond b9608's cpp-httplib vendor bump.

Improvements

  • Pulls in the latest ggml upstream state via a synchronization commit.
  • Builds on b9608's vendored cpp-httplib 0.47.0 update for the HTTP server layer.

Upgrade notes

Neither release note details the contents of the ggml sync, so treat b9610 as a low-risk housekeeping bump and validate against your own workloads. No config, API, or model-format changes are announced, so a straight binary swap should suffice. If you depend on specific ggml kernel behavior, diff the ggml submodule commit range before pinning.

Analyzed Nov 1, 2026

Upgrading?

Release notes summary

A general synchronization commit for the ggml library.

Key Highlights

  • Sync ggml

Release Notes (excerpt)

<details open> sync : ggml </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) DISABLED **Android:** - Android arm64 (CPU) **Windows:** - Windows x64 (CPU) - Windows arm64 (CPU)…

Published by ggml-org on GitHub.

Read the full release notes

Related Repositories